Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost

stdlogits/neuron-lens

A catalog of MLP neuron meanings in Qwen3-8B, read through the R-lens and from activations

Visit GitHub
Python
36
4
2 contributors
MIT License
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast stdlogits/neuron-lens is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Oct 30 – Nov 3, 2026

Stars +33 in 5 days

0102030
21

Forks +4 in 5 days

0123
3

Merged PRs 0 in 5 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Oct 30Oct 31Nov 1Nov 2Nov 3
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Fri, Oct 30, 2026+0+00
Sat, Oct 31, 2026+21+30
Sun, Nov 1, 2026+5+00
Mon, Nov 2, 2026+5+10
Tue, Nov 3, 2026+2+00
Total+33+40
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Nov 31 post

    • Sure, LLMs can be trained to read model weights, but so can a matrix. @_a9lim and I apply our recently introduced Neuron Lens to weights. It recovers the secret word in 40/40 fine-tunes and beats a…

      Read full on X, posted by @treetowntree

      @treetowntree · x.com

  2. Oct 302 posts

    • in the process of creating the database, we found a surprising number of multimodal yet monosemantic neurons in gemma 4 12b. you can learn more about them here:

      Read full on X, posted by @_a9lim

      @_a9lim · x.com

    • Learn more about Neuron Lens, how it works, and how we have progressed neuron research:

      Read full on X, posted by @treetowntree

      @treetowntree · x.com

You might also like

Repositories close to stdlogits/neuron-lens
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

lyramakesmusic/neuron-explorer

Python

Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results

1.9k224

anthropics/jacobian-lens

Python

Companion code for the global workspace interpretability paper

2.1k321

TransformerLensOrg/TransformerLens

Python

A library for mechanistic interpretability of GPT-style language models

4k718

zjunlp/Mechanist

Python

AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence

788

facebookresearch/llm-transparency-tool

Python

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo

1.3k107

WeZZard/jlens-qwen36

Python

J-space / Jacobian-lens visualizer for Qwen3.6-27B (4-bit) on Apple Silicon, ported to Apple MLX

40430

UKGovernmentBEIS/vllm-lens

Python

Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.

13922

ninjahawk/Subtext

HTML

To know what models don't say out loud.

24724

openai/transformer-debugger

Python
4.1k246