Neuron Explorer

Qwen3-0.6B

dollar sign before an amount

A neuron in layer 25 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 lights up on the dollar sign in front of a money amount, like '$7 million' or '$1 billion'. When it was turned up, the model's text drifted into odd, repetitive fragments, so the steering gave no clear theme. The opposite side reacts to degree signs after temperatures.

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

    said psychologist Jack van Honk of Utrecht University in the Netherlands, who led the study published May 24 in* Proceedings of the National Academy of Sciences*.⏎In the study, a few dozen females received half a milligram of testosterone

  2. #2 peak

    in turn protects and maintains pressure whilst keeping debris out, ensuring proper function and safety.<|endoftext|>Warner Bros./Time Warner/DC’s Wonder Woman just earned another $7 million in its seventh weekend of release, bringing the superhero movie’s domestic total

  3. #3 peak

    false positive rate as a result of mammography diagnosis results in 1.6 million unnecessary surgeries at an economical cost of over $1 billion annually in the US alone. Cyrcadia’s historic clinical results reflected

  4. #4 peak

    12 at 10:31 p.m. PDT, the world witnessed NASA’s rover landing on the Marian surface marking the next exciting phase for the $2.5 billion (USD) Mars Science Laboratory and Curiosity rover mission.

  5. #5 peak

    ⏎>>> len("a string") 8 >>> >>> s = "a long string" >>> >>> len(s) 13 >>> >>> len("") 0 >>>⏎>>> >>> s3 = '' # empty string using single quotes >>> s3

  6. #6 peak

    the space agency announced that it has awarded Elon Musk’s company a contract to build a lunar lander for its Artemis mission.⏎The contract, which is worth $2.9 billion, means that a SpaceX vehicle will be responsible for putting humans

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 potential, the growth, the growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth, growth

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

    In July, the warmest month, the average summit temperature is -19° C (-2° F).⏎When George Mallory, the British climber was

  2. #2 peak

    00, resulting in stepping angles of 30, 15, 5, 2.5, 2, and 1.8° per step.⏎Step angle = 360°/No of steps per

  3. #3 peak

    for crop pests. Some stinkbug species will not survive in extreme cold, and bean leaf beetles get knocked back when winter temperatures fall below 14° F for sustained periods of time. However, most soil insects are buffered by the

  4. #4 peak

    8°C (36° and 46°F). Do not freeze. Discard if the vaccine has

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. L21:195 strongly excites
  2. L17:38 strongly suppresses
  3. L18:48 strongly suppresses
  4. L23:35 strongly excites
  5. L20:863 excites
  6. L21:173 excites
  7. L19:131 suppresses
  8. L14:51 excites colon that introduces a statement
  9. L9:7 excites
  10. L23:474 excites
  11. L16:170 suppresses
  12. L10:33 suppresses
  13. L15:123 suppresses
  14. L2:204 suppresses
  15. L14:348 suppresses
  16. L20:8 suppresses
  17. L18:267 excites
  18. L20:603 excites
  19. L21:130 suppresses
  20. L16:2 suppresses
  21. L2:761 excites
  22. L18:887 excites
  23. L19:187 excites
  24. L1:8 excites

Feeds later layers

  1. L26:365 strongly excites
  2. L26:56 strongly suppresses
  3. L27:744 strongly suppresses
  4. L27:1113 strongly excites
  5. L26:919 strongly excites
  6. L27:166 strongly excites
  7. L27:1432 strongly suppresses
  8. L27:462 excites
  9. L27:1471 excites
  10. L26:800 suppresses
  11. L26:2026 excites
  12. L26:3057 suppresses
  13. L27:1144 excites
  14. L26:1513 excites
  15. L26:174 excites
  16. L26:383 excites
  17. L27:138 excites
  18. L27:662 excites
  19. L27:660 excites
  20. L27:334 excites
  21. L27:875 excites
  22. L27:327 suppresses
  23. L26:2053 suppresses
  24. L27:1098 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.

2 values between -21.91 and -20.602 values between -18.00 and -16.691 values between -15.39 and -14.091 values between -14.09 and -12.782 values between -11.48 and -10.182 values between -8.87 and -7.574 values between -7.57 and -6.262 values between -6.26 and -4.9612 values between -4.96 and -3.669 values between -3.66 and -2.3515 values between -2.35 and -1.053577 values between -1.05 and 0.25266 values between 0.25 and 1.565 values between 1.56 and 2.863 values between 2.86 and 4.161 values between 5.47 and 6.773 values between 8.08 and 9.381 values between 28.93 and 30.23offnegativepositiveoften

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. #c
  2. #w
  3. [z
  4. @a
  5. {j
  6. [v
  7. [w
  8. {k
  9. {i
  10. [y

Suppresses

  1. (
  2. [
  3. -
  4. _
  5. <
  6. /
  7. *
  8. (?:
  9. 🏾
  10. \