Neuron Explorer

Qwen3-0.6B

'known' after 'better' or 'also'

A neuron in layer 19 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 fires on the word 'known' when it comes right after phrases like 'better known as' or 'also known as'. When it was turned up, the text drifted into repeating the word 'difference' over and over.

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

    ived people around the world. Arguably, the most famous and relevant of these compounds is 1,3,7-trimethylxanthine, better known as caffeine.⏎It’s pretty common knowledge that caffeine, at least in a very

  2. #2 peak

    , a tropical forest in Panama. Their method was simple: They drilled holes into the trees and waited.⏎Wsiclo and his<|endoftext|>Eric Weisz, better known to the world as Harry Houdini,

  3. #3 peak

    . Bruce Weinstein, better known to some as The Ethics Guy, listed five of them in his book Ethical

  4. #4 peak

    minated in the capture and destruction of Jerusalem. Titus became the Roman emperor in 79. He completed construction of the Flavian Amphitheatre, better known as the Colosseum, and opened it with ceremonies lasting more than

  5. #5 peak

    ilded Age architect who was a friend and admirer.⏎And it would be a surprise to almost everyone that the 94-by-94-foot laboratory, known as Wardenclyffe and envisioned by Tesla as a prototype for a stupend

  6. #6 peak

    , the sun god, wearing a crown of rays graces the obverse. This image was based upon the head of the great statue of Helios, better known as the Colossus of Rhodes, one of the Seven Wonders of the

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 difference between the difference and the difference. The difference is the difference from the difference from the difference, the difference from the difference from the difference, etc. The difference from the difference from the difference is the main difference. The difference from

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

    What Are the Issues Concerning Empathy?⏎- What Is Compassion?⏎- What Are the Issues Concerning Compassion?⏎- Compassion vs Empathy: What Is the Difference?⏎What Is Empathy?⏎Empathy is the ability to put

  2. #2 peak

    !<|endoftext|>How to Graph a Cotangent Function⏎The parent graphs of tangent and cotangent are comparable because they both have asymptotes and x-intercepts. The only differences you can see are the values of theta where the asymptotes and x-inter

  3. #3 peak

    bellies and chest. They can have gray patches, however, which sometimes causes them to be mistaken for their cousin the gray fox. The best way to tell the difference is to check the tail: gray foxes have a black tipped tails<|endoftext|>

  4. #4 peak

    . To tell the truth slant is a way to get around the entire truth, without lying.⏎3. What is the major difference between the two expressions?⏎The differences between the two expressions are that one is very blatant and obvious while the other

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. L17:2817 suppresses
  2. L11:363 excites
  3. L15:1952 suppresses
  4. L15:1585 suppresses
  5. L17:1834 suppresses
  6. L2:2246 excites
  7. L12:2285 suppresses
  8. L14:1773 weakly excites
  9. L16:3009 weakly suppresses
  10. L15:3011 weakly excites
  11. L15:1741 weakly excites
  12. L4:2520 weakly suppresses
  13. L6:1423 weakly suppresses
  14. L17:2458 weakly excites
  15. L18:1277 weakly suppresses
  16. L6:1608 weakly excites
  17. L7:2470 weakly excites
  18. L13:515 weakly suppresses
  19. L18:2654 weakly excites
  20. L14:2329 weakly suppresses
  21. L11:2664 weakly excites
  22. L17:1531 weakly suppresses
  23. L17:2773 weakly suppresses
  24. L9:96 weakly suppresses

Feeds later layers

  1. L27:2511 strongly suppresses
  2. L25:648 strongly suppresses
  3. L23:1955 suppresses
  4. L21:2185 suppresses
  5. L24:2557 suppresses
  6. L27:1903 suppresses
  7. L22:2143 suppresses
  8. L23:1897 suppresses
  9. L23:934 suppresses
  10. L21:2973 suppresses
  11. L23:1721 suppresses
  12. L22:1337 suppresses
  13. L22:1410 suppresses
  14. L21:2200 weakly suppresses
  15. L21:1955 weakly suppresses
  16. L20:1812 weakly suppresses
  17. L23:2589 weakly suppresses
  18. L22:1793 weakly suppresses
  19. L27:1881 weakly suppresses
  20. L21:1090 weakly suppresses
  21. L23:875 weakly suppresses
  22. L27:1492 weakly suppresses
  23. L20:795 weakly excites
  24. L21:2473 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 -38.00 and -36.751 values between -11.83 and -10.581 values between -9.34 and -8.091 values between -8.09 and -6.841 values between -6.84 and -5.602 values between -5.60 and -4.355 values between -4.35 and -3.1023 values between -3.10 and -1.86125 values between -1.86 and -0.613589 values between -0.61 and 0.64134 values between 0.64 and 1.8811 values between 1.88 and 3.137 values between 3.13 and 4.371 values between 4.37 and 5.622 values between 5.62 and 6.873 values between 6.87 and 8.111 values between 10.61 and 11.85offnegativepositiveoften

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. UGIN
  2. iasm
  3. otos
  4. rette
  5. 他自己
  6. eled
  7. osos
  8. eper
  9. 打折
  10. (units

Suppresses

  1. difference
  2. differences
  3. Difference
  4. difference
  5. 差异
  6. Difference
  7. 区别
  8. Differences
  9. diferença
  10. 差别