Neuron Explorer

Qwen3-0.6B

'Springer' and 'rebirth' style word pieces

A neuron in layer 0 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron responds to a mixed bunch of words, most often the publisher name Springer, and parts of words like 'rebirth' and 'astronaut'. Turning it up or down did not produce a clear change in what the model wrote.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    , Vol 3118, Springer-Verlag, Berlin⏎Heidelberg New York⏎D., Lenoir

  2. #2 peak

    , filters, scripts and many basic or more advanced topics. It also includes some tutorials.⏎by Nicholas M. Patrikalakis, Takashi Maekawa - Springer⏎Shape interrogation is the process of

  3. #3 peak

    from East Side Charter, Springer Middle School, and H.B. duPont Middle School.⏎The project, which

  4. #4 peak

    had 9 foot ceilings and noticeable window decorations.⏎Gothic architecture is typified by simply the use regarding large, featureless rooftops. The Gothic rebirth style was personified by beautiful monasteries which had huge, domes,

  5. #5 peak

    03 and repeated it a few times since then.⏎But there were two new dimensions of the recent flight. One, it carried a Chinese woman astronaut into space for the first time. Secondly and far more significantly, it demonstrated China

  6. #6 peak

    SS: Adaptable⏎The State of the Union Address⏎Introduce your future voters to the annual State of the Union Address. The day after the speech airs on television, use the activity from PBS to discuss 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: I am writing a paper on a research about a study on a paper on a paper on a paper. I need to write a paper on a research paper. I am writing a paper. I need to write a paper. I need to

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

    the synergy of every team member.⏎n.大綱, 提要 [ summary or outline of a book, play, etc ]⏎note: 字根

  2. #2 peak

    Paris to Petersburg in one hour'). The print shows a man seated on a steam-powered rocket-like contraption, which is propelling him through the sky above the rooftops and spires of a town. It is a German version of an English

  3. #3 peak

    .⏎The root of all energy on Earth is the Sun. The logical source for renewable energy is Solar power. One problem is the size of solar panels - you gotta cover the roof of your house with junk just to have enough umph boil a

  4. #4 peak

    the impact of the environment.<|endoftext|>5 COMMON CAUSES OF BRAIN FOG⏎You need to stop by the grocery on the way home from work for two gotta-have items.

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. L3:3037 suppresses
  2. L21:2252 suppresses
  3. L19:1016 excites
  4. L26:2929 weakly excites
  5. L11:1799 weakly suppresses
  6. L17:3041 weakly excites
  7. L1:2094 weakly excites
  8. L7:2579 weakly excites
  9. L17:451 weakly suppresses
  10. L20:2097 weakly suppresses
  11. L19:1654 weakly excites
  12. L24:2770 weakly suppresses
  13. L4:2144 weakly suppresses
  14. L21:1781 weakly excites
  15. L18:1955 weakly excites
  16. L22:2651 weakly excites
  17. L19:2934 weakly excites
  18. L17:1863 weakly excites
  19. L18:1745 weakly excites
  20. L21:2033 weakly excites
  21. L13:624 weakly excites
  22. L25:1138 weakly excites
  23. L23:2737 weakly excites
  24. L23:1983 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 -0.77 and -0.741 values between -0.69 and -0.661 values between -0.63 and -0.611 values between -0.61 and -0.582 values between -0.50 and -0.471 values between -0.47 and -0.441 values between -0.44 and -0.411 values between -0.41 and -0.394 values between -0.39 and -0.361 values between -0.36 and -0.331 values between -0.33 and -0.303 values between -0.30 and -0.288 values between -0.28 and -0.258 values between -0.25 and -0.2213 values between -0.22 and -0.1920 values between -0.19 and -0.1751 values between -0.17 and -0.14103 values between -0.14 and -0.11149 values between -0.11 and -0.08359 values between -0.08 and -0.06626 values between -0.06 and -0.03942 values between -0.03 and -0.00902 values between -0.00 and 0.03316 values between 0.03 and 0.05192 values between 0.05 and 0.0894 values between 0.08 and 0.1140 values between 0.11 and 0.1426 values between 0.14 and 0.1617 values between 0.16 and 0.1910 values between 0.19 and 0.224 values between 0.22 and 0.253 values between 0.25 and 0.272 values between 0.27 and 0.305 values between 0.30 and 0.33offnegativepositiveoften

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. ăm
  2. 胎
  3. imposs
  4. 不可思
  5. anism
  6. aż
  7. mates
  8. Impossible
  9. igit
  10. kil

Suppresses

  1. ave
  2. обязательно
  3. Doc
  4. 更多
  5. Prompt
  6. ernet
  7. 祚
  8. AreaView
  9. olean
  10. indoors