Source: https://events.trymimetic.com/events/sf/learning-layer-paper-reading-club-week-38-neural-networks-are-already-clean-nov

# Learning Layer Paper Reading Club - Week 38 - Neural Networks Are Already CleanSan Francisco, November 2026

**This event has ended.**
Upcoming San Francisco events are listed below.

When
:   Tuesday, November 3, 2026, 5:30 PM to 7:30 PM Pacific Time (PST)

Where
:   [Homebrew Club, 111 Maiden Ln #540, San Francisco, CA 94108, USA](/events/venue/homebrew-club)

City
:   San Francisco, CA

Format
:   In person

Cost
:   Free

Organiser
:   Learning Layer Labs, Thomas, Mat Allen and 2 more

Listing
:   [The original listing on Luma](https://lu.ma/learning-6j9t?utm_source=trymimetic&utm_medium=calendar&utm_campaign=ai_events)

## About This Event

**This week's reading:**
Neural Networks Are Already Clean (Nick Cammarata, Goodfire)

Link: <https://already-clean.goodfire.com/>

**About the session:**

A common view in interpretability is that neural networks are tangled knots: individual neurons do several unrelated jobs (polysemanticity), because networks cram more concepts than they have room for into shared neurons (superposition). If that is right, you cannot study neurons directly and need tools like sparse autoencoders to unfold the network first.

This essay argues the opposite. It revisits classic examples such as the InceptionV1 "cat and car" neuron and re-reads them as ordinary features like V-shape and pose detectors. It then looks at vision models of very different sizes and at language-model neurons in Qwen3-32B. The author's claim is that most apparent polysemanticity comes from fixable causes (weak visualization tools, missing architecture features, thin datasets) and from neurons growing in several directions over training, not from superposition.

Thomas will walk through the post, then step back and cover some wider AI interpretability concepts at a high level, so you do not need a background in the field.

Relevant to anyone curious about how models work inside, from newcomers to interpretability to people who have used SAEs. No preparation required. Come read and discuss with us.

Thomas will lead the discussion this week.

### **What is the Learning Layer Labs Paper Reading Club?**

An initiative from <https://www.learninglayer.ai>, a lab with the goal of reducing AI anxiety in the world.

**What is the format?**

Discussion based. Expect a low pressure environment to share insights and opinions with the group.

**What are the group goals?**

Stay on top of AI research and improve understanding of AI fundamentals + math.

**Who is welcome?**

Everyone! Try to put in at least some time on the paper and come prepared with questions or things you'd like to discuss, but it's ok to just show up!

**Learning Layer Labs team:**

- [Thomas Redfern](https://www.linkedin.com/in/thomas-redfern/?utm_source=luma) ( The backbone who runs every paper reading )
- [Mat Allen](https://www.linkedin.com/in/mat-allen-2bbb251b1/?utm_source=luma) (The new fella bring order and organization)
- [Devinder Sodhi](https://www.linkedin.com/in/devindersodhi/?utm_source=luma) (The guy you talk to for sponsoring)

## Hosted by

[Learning Layer Labs](https://luma.com/learninglayerlabs)

[Thomas](https://luma.com/user/tms7331)

[Mat Allen](https://luma.com/user/usr-gEwcJEkvbiqZwEL)

[Devinder Sodhi (LLL)](https://luma.com/user/devsodhirao)

[Amitabh Das](https://luma.com/user/usr-XiGOkPjrdhUhzai)

AI

Networking

Talk

Research

[See the original listing](https://lu.ma/learning-6j9t?utm_source=trymimetic&utm_medium=calendar&utm_campaign=ai_events)

[20 more SF AI events this week](/events/ai/sf)

Site check

## See what's costing your site sales

See how your website, messaging, and go-to-market strategy stack up, in minutes.

[Check my site](/?utm_source=events&utm_medium=referral&utm_campaign=ai&utm_content=event_detail_cta)

## Coming up in San Francisco

### [The Commons Public Hours ☕](/events/sf/the-commons-public-hours-nov-2026-2)

Today · 9:00 AM PT
TBD
5 attending

### [SF Writing Club](/events/sf/sf-writing-club-nov-2026-2)

Today · 10:00 AM PT
TBD
1 attending

### [Festiverse 2026: Diwali Hackathon](/events/sf/festiverse-2026-diwali-hackathon-nov-2026)

Tomorrow · 9:30 AM PT
AWS Builder Loft, First Market Tower, 525 Market St Entrance, San Francisco, CA 94105, USA

### [Build Lean, Scale Global: India’s STEM Talent to Fundings from UAE & Singapore (Multiplayer AI Special Session)](/events/sf/build-lean-scale-global-indias-stem-talent-to-uae-singapore-markets-multiplayer)

Tomorrow · 3:30 PM PT
AWS Builder Loft, First Market Tower, 525 Market St Entrance, San Francisco, CA 94105, USA
72 attending

### [Founders Demo Night | YC, The Residency & More](/events/sf/founders-demo-night-yc-the-residency-more-nov-2026)

Tomorrow · 5:00 PM PT
San Francisco, California

### [Founder Friendsgiving Dinner](/events/sf/founder-friendsgiving-dinner-nov-2026)

Tomorrow · 5:30 PM PT
San Francisco, CA

[← Back to San Francisco Events](/events/ai/sf)
