Neuron Explorer

Qwen3-0.6B

end of document token

A neuron in layer 12 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 responds strongly to the invisible marker that ends a web page and comes right before a new, unrelated page. It goes quiet on the words 'granted' and 'possible' in phrases like 'take for granted'. Turning it up gave off-topic text.

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

    to Simplify Expressions⏎A straight forward approach to simplifying expressions⏎Integer Practice Problems - Addition⏎Review and Practice Problems for adding positive and negative numbers⏎<|endoftext|>In physics, a conservation law states that a particular measurable property of an isolated physical

  2. #2 peak

    VS is a promising alternative strategy to produce the functional and thermostable reverse transcriptase.⏎All Science Journal Classification (ASJC) codes⏎- Insect Science<|endoftext|>An account of the religion of

  3. #3 peak

    994- Drexel University. All rights reserved.⏎The Math Forum is a research and educational enterprise of the Drexel University School of Education.<|endoftext|>Maybe you’ve tried intermittent fasting (IF) to shed a few (pand

  4. #4 peak

    this word list.⏎List shorter words within focus, sorted by length⏎All words formed from focus by changing one letter⏎Browse words starting with focus by next letter<|endoftext|>I was listening to Brooke Gladstone's ON THE MEDIA podcast about the difficulty of

  5. #5 peak

    liu.<|endoftext|>Bond Price Calculator⏎With this bond price calculator, we aim to help you calculate

  6. #6 peak

    You can submit your school, college or university level homework or assignment to us and we will make sure that you get the answers related to classification of relays.<|endoftext|>Harvest Strike Call--Pickets gather at the edge of a Central California grape

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: I am so glad that we have such a good time. I mean, so much better than I had. This is so precious. I can't think of anything so great. I am so lucky. I have access to all the good

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

    and screen for a host of maladies thanks to sophisticated imaging technology. X-rays are now so frequently used and so effective that most of us take their capabilities for granted—but it was not so long ago a tumor or damaged bone couldn’t be found

  2. #2 peak

    into a true and genuine spiritual experience.⏎If you’re reading this article, it’s thanks to the generosity of people like you, who have made Aleteia possible.⏎Here<|endoftext|>The

  3. #3 peak

    remarkable feats of science have been accomplished. What people fifty years ago would have sworn would always be the product of Science Fiction are now everyday realities that we take for granted. Products like our smartphones,

  4. #4 peak

    1, 47, and 48. Here again praise moves into a yet higher sphere, and consists of an expression of thankfulness to God for what He is in Himself in mercy.⏎These movements indicate a growth of experience, center

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. L10:2464 excites
  2. L11:1909 excites
  3. L10:507 suppresses
  4. L4:833 weakly suppresses
  5. L8:2870 weakly excites
  6. L10:1946 weakly suppresses
  7. L9:1507 weakly excites
  8. L9:1735 weakly suppresses
  9. L11:1933 weakly suppresses
  10. L2:2328 weakly suppresses
  11. L4:21 weakly excites
  12. L3:272 weakly excites
  13. L1:2278 weakly excites
  14. L0:2661 weakly excites
  15. L5:2875 weakly suppresses
  16. L6:1379 weakly excites
  17. L3:115 weakly suppresses
  18. L3:1703 weakly excites
  19. L11:1924 weakly suppresses
  20. L2:122 weakly excites
  21. L9:835 weakly suppresses
  22. L9:2068 weakly suppresses
  23. L8:777 weakly suppresses
  24. L11:5 weakly suppresses

Feeds later layers

  1. L13:1719 suppresses
  2. L18:1843 weakly suppresses
  3. L18:2252 weakly excites
  4. L15:2426 weakly suppresses
  5. L13:2205 weakly suppresses
  6. L13:2688 weakly suppresses
  7. L14:1669 weakly suppresses
  8. L16:2920 weakly suppresses
  9. L26:2963 weakly excites
  10. L13:1817 weakly suppresses
  11. L17:1671 weakly excites
  12. L19:613 weakly excites
  13. L21:2074 weakly suppresses the word 'later' after a time span
  14. L14:771 weakly suppresses
  15. L26:9 weakly excites
  16. L18:2800 weakly excites
  17. L22:740 weakly excites
  18. L16:1622 weakly suppresses
  19. L19:1297 weakly excites
  20. L24:447 weakly excites square bracket opening an inserted note
  21. L23:1201 weakly excites
  22. L24:2242 weakly excites
  23. L23:2048 weakly excites
  24. L24:1003 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.

2 values between -0.71 and -0.625 values between -0.62 and -0.5414 values between -0.54 and -0.4551 values between -0.45 and -0.3791 values between -0.37 and -0.28220 values between -0.28 and -0.20335 values between -0.20 and -0.12572 values between -0.12 and -0.03730 values between -0.03 and 0.05674 values between 0.05 and 0.14478 values between 0.14 and 0.22342 values between 0.22 and 0.31182 values between 0.31 and 0.39100 values between 0.39 and 0.4857 values between 0.48 and 0.5626 values between 0.56 and 0.6417 values between 0.64 and 0.735 values between 0.73 and 0.812 values between 0.81 and 0.901 values between 0.90 and 0.981 values between 1.24 and 1.321 values between 1.49 and 1.571 values between 2.50 and 2.591 values between 2.59 and 2.67offnegativepositiveoften

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. nings
  2. heads
  3. [opt
  4. ickle
  5. +self
  6. (lines
  7. ningen
  8. $_[
  9. чество
  10. ].[

Suppresses

  1. 还好
  2. 暴力
  3. 富贵
  4. 幸好
  5. privilege
  6. 高楼
  7. ilege
  8. epam
  9. 感谢
  10. 运行