Neuron Explorer

Qwen3-0.6B

end-of-document marker token

A neuron in layer 0 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 hidden end-of-text marker that separates one web page or document from the next. Turning it up made the model's writing wander into unrelated topics, with no clear theme.

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

    if not server_response['successful']:⏎etag = server_response['file_handle'].info().getheader('ETag')⏎xml_document = server_response['xml_document']<|endoftext|>Deepak Vashishth, assistant professor of biomedical engineering, hopes that his

  2. #2 peak

    одальные глаголы и их эквиваленты и выполните следующее задание:⏎а) заполните пропуски<|endoftext|>Last Updated February

  3. #3 peak

    glad it wasn't just us who saw the poor editing.”⏎‘golden-eye’ hasn't been added to any lists yet.⏎Looking for tweets for golden-eye.<|endoftext|>New subjects guide for primary years⏎Designated

  4. #4 peak

    Paper 294.⏎Loma Linda University Electronic Theses and Dissertations⏎Loma Linda University. Del E. Webb Memorial Library. University Archives<|endoftext|>Category Archives: History⏎There were eighteen African-American athletes

  5. #5 peak

    -12⏎Latest update: 2011-JUN-19⏎Author: B.A. Robinson⏎This page translator works on Firefox,<|endoftext|>It looks like you're using Internet Explorer 11 or older

  6. #6 peak

    Otago’s Department of Psychology, says “we may have to seriously re-think the use of the term ‘bird brain’ as a put down.”<|endoftext|>While doing research in a local newspaper for my ancestors in Harvard, Illinois, I

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: a new idea. Let me present this new idea to you. It is the idea that I have been thinking about lately. Let me present this new idea to you. It is the idea that I have been thinking about lately. Let me

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

    Meng Haoran⏎Era Meng Haoran Major poet during the Tang Dynasty Setting of Spring Dawn⏎Meaning for Line 1 春 : spring 眠 : sleep 不 : not 觉 : to feel, wake up 晓

  2. #2 peak

    it in more detail, because it’s a really cool parasite, as well as in the center of much research nowadays.⏎Wolbachia are Gram-negative ⍺-Proteobacteria (order Rickettsiales, family Anapl

  3. #3 peak

    , 24 = 4 ⋅ 6. So to solve the second part, on average, we need

  4. #4 peak

    With time we check more numbers and become more convinced that the conjecture is true. Currently, it has been checked up to the power 4.6 ⋅<|endoftext|>Picture Yourself in Orbit: Are You Really Weightless?⏎An object in

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

None: this is the first layer.

Feeds later layers

  1. L9:303 excites end-of-document token
  2. L5:236 excites
  3. L6:407 excites end-of-text token after a web page
  4. L26:1 weakly suppresses
  5. L1:1592 weakly suppresses
  6. L26:2977 weakly suppresses
  7. L24:2340 weakly suppresses
  8. L24:2775 weakly excites
  9. L26:1449 weakly suppresses
  10. L13:1681 weakly suppresses
  11. L15:694 weakly excites
  12. L23:44 weakly excites
  13. L27:2105 weakly suppresses
  14. L18:627 weakly suppresses
  15. L4:41 weakly excites
  16. L24:224 weakly excites
  17. L17:2864 weakly suppresses
  18. L9:1641 weakly suppresses
  19. L1:3017 weakly suppresses
  20. L3:269 weakly excites
  21. L4:204 weakly suppresses
  22. L25:2540 weakly suppresses
  23. L6:2101 weakly excites
  24. L2:1771 weakly suppresses

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.

34 values between -0.49 and -0.183791 values between -0.18 and 0.1373 values between 0.13 and 0.441 values between 0.44 and 0.751 values between 9.41 and 9.721 values between 10.34 and 10.651 values between 10.65 and 10.962 values between 10.96 and 11.271 values between 11.27 and 11.583 values between 11.58 and 11.89offnegativepositiveoften

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. ChildIndex
  2. ushi
  3. configuration
  4. .Profile
  5. 📢
  6. #${
  7. ATFORM
  8. ENTION
  9. .CONFIG
  10. Alphabet

Suppresses

  1. own
  2. iders
  3. vars
  4. own
  5. rates
  6. Rates
  7. чество
  8. idor
  9. orde
  10. edd