Neuron Explorer

Qwen3-0.6B

copyright and rights notices

A neuron in layer 14 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron responds to the end of copyright lines, such as 'All rights reserved' or '© 2018 Author'. These are the boilerplate lines that appear at the bottom of web pages and papers. Turning it up did not bring out a copyright theme in the writing.

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

    trends in NCD prevalence, their risk factors, and treatments.⏎Copyright © 2020 The Royal Society for Public Health. Published by Elsevier Ltd. All rights reserved.<|endoftext|>We all grew up hearing the phrase, “Good night

  2. #2 peak

    1 DOI:http://dx.doi.org/10.4314/aas.v15i2.5⏎© 2018 Author. This work is licensed under the Creative Commons Attribution 4.0 International License

  3. #3 peak

    iquette and Responsibilities Brochure.<|endoftext|>Portuguese translation of 'discontent'⏎Copyright © 2014 by HarperCollins Publishers. All rights reserved.⏎Example Sentences Including 'discontent'⏎Marriage, discontent with home,

  4. #4 peak

    other nine were found to be “obstructive.”<|endoftext|>Rural earthen roads impact assessment in Phewa watershed, Western region, Nepal⏎© The Author(s). 2016⏎Received: 23 November 2

  5. #5 peak

    and Other Writings (1971).⏎The Columbia Electronic Encyclopedia, 6th ed. Copyright © 2012, Columbia University Press. All rights reserved.⏎See more Encyclopedia articles on

  6. #6 peak

    , China⏎2 Nanjing Xiaozhuang University, Nanjing, Jiangsu 211171, China⏎*Authors to whom correspondence should be addressed.⏎Received: 2020-8-4 / Accepted

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: The effect of a small amount of information. The effect of a small amount of information. The effect of a small amount of information. The effect of a small amount of information. The effect of a small amount of information. The effect of

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

    015 framework and its preparation if poverty is to be taken more seriously by donors.⏎|Date of creation:||2013|⏎|Date of revision:|⏎|Contact details of

  2. #2 peak

    last during His, not one another's pleasure.⏎This idea found its way into our Declaration of Independence in modified form:⏎We hold these truths to be self-evident, that all men are created equal, that they are endowed by their Creator

  3. #3 peak

    We hold these Truths to be self-evident, that all Men are created equal, that they are endowed by their Creator

  4. #4 peak

    Pakistan⏎||It has been suggested that this article be merged with Blasphemy law#Pakistan. (Discuss) Proposed since March 2

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. L13:8 excites
  2. L10:169 weakly excites
  3. L4:181 weakly suppresses
  4. L13:2974 weakly excites
  5. L11:1475 weakly suppresses unclear: end of boilerplate text
  6. L10:2279 weakly excites
  7. L12:2177 weakly suppresses
  8. L12:2642 weakly suppresses
  9. L10:2818 weakly suppresses
  10. L12:405 weakly excites
  11. L13:1762 weakly suppresses
  12. L13:1277 weakly excites
  13. L2:62 weakly excites
  14. L10:2696 weakly excites
  15. L6:1672 weakly suppresses
  16. L9:2736 weakly suppresses
  17. L11:853 weakly excites
  18. L8:2628 weakly suppresses
  19. L1:533 weakly excites
  20. L4:564 weakly excites
  21. L3:795 weakly excites
  22. L2:2091 weakly excites
  23. L13:428 weakly suppresses
  24. L9:2863 weakly excites

Feeds later layers

  1. L16:1427 excites
  2. L18:1817 excites
  3. L20:309 excites
  4. L16:2247 weakly suppresses
  5. L19:2173 weakly suppresses
  6. L21:1985 weakly excites
  7. L15:2675 weakly excites
  8. L16:3064 weakly excites
  9. L15:2597 weakly suppresses end of a web document
  10. L15:1726 weakly suppresses
  11. L15:2861 weakly suppresses 'only' in 'not only ... but'
  12. L23:2395 weakly excites
  13. L25:381 weakly suppresses
  14. L20:1774 weakly excites
  15. L20:1539 weakly suppresses
  16. L21:2855 weakly excites
  17. L19:1758 weakly excites
  18. L17:1398 weakly suppresses
  19. L18:720 weakly excites
  20. L21:2170 weakly excites
  21. L18:412 weakly suppresses
  22. L18:1403 weakly suppresses
  23. L16:370 weakly suppresses
  24. L23:340 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.

1 values between -2.72 and -2.611 values between -2.29 and -2.191 values between -1.65 and -1.542 values between -1.01 and -0.901 values between -0.69 and -0.585 values between -0.58 and -0.4730 values between -0.47 and -0.36104 values between -0.36 and -0.26353 values between -0.26 and -0.15715 values between -0.15 and -0.041098 values between -0.04 and 0.07845 values between 0.07 and 0.17457 values between 0.17 and 0.28204 values between 0.28 and 0.3972 values between 0.39 and 0.4915 values between 0.49 and 0.602 values between 0.60 and 0.711 values between 1.24 and 1.351 values between 1.46 and 1.57offnegativepositiveoften

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. WALL
  2. aña
  3. ron
  4. !⏎⏎⏎⏎⏎⏎
  5. tron
  6. ACHI
  7. !⏎⏎⏎
  8. achi
  9. Tri
  10. tical

Suppresses

  1. INESS
  2. stinence
  3. fict
  4. onders
  5. 肱
  6. stash
  7. estival
  8. 取证
  9. hypothetical
  10. evidence