Neuron Explorer

Qwen3-0.6B

spot right before a number

A neuron in layer 13 of Qwen3-0.6B. Its strongest snippets are very consistent: they mostly peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron reacts to the word or space just before a number is about to appear, like 'born in' followed by a year, or 'There were' followed by a count. Turning it up did not produce a clear theme in the replies.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

  1. #1 peak

    (6-8) Show all Grade Level⏎Resource Type: Activities⏎Results 1 - 7 of 7 matches⏎From Grid

  2. #2 peak

    Shoguns.⏎It is also known that there was once an ancient civilisation in the area pre<|endoftext|>- Herbert A. Simon was an American scientist born in 1916.⏎- He is most famous for his work in the field

  3. #3 peak

    during the final manned flight of the Skylab space station in 1973 and 1974.⏎He was born January 23, 1930, in Okemah, Oklahoma. He received a Bachelor

  4. #4 peak

    and 1.79% from two or more races. Hispanic or Latino of any race were 0.89% of the population.⏎There were 46 households out of which 28.3% had children under the

  5. #5 peak

    jing Xiaozhuang University, Nanjing, Jiangsu 211171, China⏎*Authors to whom correspondence should be addressed.⏎Received: 2020-8-4 / Accepted: 202

  6. #6 peak

    created with an extra letter added to rifts:⏎24 words found using the letters in "Rifts"⏎5 Letter Words⏎4 Letter Words⏎3 Letter Words⏎2 Letter Words<|endoftext|>Marx and Engels' work covers a wide

Steering

Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.

turned down a lot
Prompt

Here is something I have been thinking about lately: and I want to know about this, and also to know about this, and also to know about this, and also to know about this, and also to know about this, and also to know about this, and also to know about

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

  1. #1 peak

    in Education (eJSiE):⏎2, Article 1.⏎Available at: http://epublications.bond.edu.au/ejsie/vol8/iss2/1<|endoftext|>Some may argue that sleeping is one of the best parts

  2. #2 peak

    last edited on: 2008-09-09 15:47:35⏎Did you find this article helpful? Yes No⏎How can we improve this article?<|endoftext|>Java tutorials

  3. #3 peak

    adapt. [Awareness of climate change] is<|endoftext|>- Created by: Luke Simons⏎- Created on: 06-04-12 19:17⏎1. Newton's model of the universe made four

  4. #4 peak

    here. There are several questions in this exercise. Our subject expert teachers have solved each of these questions in a step by step manner. All these solutions are beneficial for the students of class 10 appearing for the board exams. Students can easily

Connections

Show on map

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Fed by earlier layers

  1. L12:2530 weakly suppresses
  2. L6:940 weakly suppresses
  3. L9:857 weakly excites
  4. L11:2083 weakly excites
  5. L7:1558 weakly excites
  6. L8:424 weakly suppresses
  7. L12:1045 weakly suppresses
  8. L9:2396 weakly suppresses
  9. L11:546 weakly suppresses
  10. L8:229 weakly excites
  11. L5:496 weakly suppresses
  12. L12:2177 weakly suppresses
  13. L6:725 weakly excites
  14. L4:2456 weakly excites
  15. L8:2893 weakly suppresses
  16. L10:1553 weakly suppresses
  17. L10:2598 weakly excites
  18. L9:50 weakly suppresses
  19. L11:1022 weakly excites
  20. L8:339 weakly excites
  21. L8:1761 weakly excites
  22. L7:2272 weakly suppresses
  23. L10:2939 weakly suppresses
  24. L7:2464 weakly excites

Feeds later layers

  1. L17:2529 suppresses
  2. L14:1002 weakly excites
  3. L17:2535 weakly excites
  4. L25:3049 weakly suppresses
  5. L16:1920 weakly excites
  6. L15:339 weakly excites
  7. L20:631 weakly suppresses
  8. L17:2704 weakly suppresses
  9. L19:2601 weakly suppresses
  10. L15:234 weakly suppresses
  11. L18:2581 weakly suppresses
  12. L14:2788 weakly suppresses
  13. L17:1078 weakly excites
  14. L14:2439 weakly excites
  15. L27:1205 weakly excites
  16. L18:266 weakly excites
  17. L16:2568 weakly excites
  18. L14:2298 weakly suppresses
  19. L14:229 weakly suppresses
  20. L14:1051 weakly excites
  21. L16:1380 weakly excites
  22. L14:2559 weakly suppresses
  23. L27:376 weakly suppresses
  24. L16:2337 weakly excites

Activation histogram

How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.

1 values between -1.58 and -1.491 values between -1.40 and -1.301 values between -1.21 and -1.121 values between -1.12 and -1.031 values between -1.03 and -0.931 values between -0.93 and -0.844 values between -0.84 and -0.757 values between -0.75 and -0.668 values between -0.66 and -0.5710 values between -0.57 and -0.4716 values between -0.47 and -0.3848 values between -0.38 and -0.2994 values between -0.29 and -0.20242 values between -0.20 and -0.10974 values between -0.10 and -0.011788 values between -0.01 and 0.08416 values between 0.08 and 0.17160 values between 0.17 and 0.2659 values between 0.26 and 0.3629 values between 0.36 and 0.4517 values between 0.45 and 0.542 values between 0.54 and 0.638 values between 0.63 and 0.737 values between 0.73 and 0.824 values between 0.82 and 0.911 values between 0.91 and 1.001 values between 1.00 and 1.093 values between 1.19 and 1.281 values between 1.28 and 1.372 values between 1.46 and 1.551 values between 2.02 and 2.11offnegativepositiveoften

Logit lens

The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layers instead.

Promotes

  1. iments
  2. agram
  3. VES
  4. getService
  5. ungle
  6. شف
  7. LAS
  8. 工业大学
  9. uffers
  10. visualization

Suppresses

  1. 带
  2. 甚至是
  3. or
  4. 或者
  5. 甚至
  6. 存在
  7. çekil
  8. chap
  9. 自理
  10. 印