Neuron Explorer

Qwen3-0.6B

muscle and body movement words

A neuron in layer 9 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 lights up on words about muscles and the body moving, such as 'flex', 'muscle', 'hip flexors' and 'stretching', though it also fires on some unrelated words like 'picky'. Turning it up made the model's writing wander off into random topics like coffee and weather, so the steering shows no clear theme.

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

    inal (belly) muscles support the spine from the front and sides of the body.⏎- Iliopsoas muscles support the spine and flex the hips.⏎- Erector spinae muscles support the back of the trunk

  2. #2 peak

    Just like any other sport, training in swimming is important. One of the quality training is a good nutrition. A learner also has to develop and strengthen your mental muscle son regular basis. Look for help in learning new strokes technique. In case the

  3. #3 peak

    be supplemented with a humidifier to make the air moister.⏎You might actually be the one responsible for frequent nose bleeds. Bad habits such as nose-picking can increase the chances of nose bleeds. Because the membrane and blood vessels inside

  4. #4 peak

    on purees and become picky eaters, especially if they get used to extremely smooth purees. However,

  5. #5 peak

    body.⏎Move More Muscles⏎Most of the muscles you use in running are in your lower body: your quads, hamstrings, glutes, hip flexors and calves

  6. #6 peak

    seeing among clients for less intensive fitness routines that are accessible and mesh with an on-the-go lifestyle.⏎Why gardening is exercise⏎Gardening engages all the major muscle groups, such as the arms, legs, shoulders, back and abdomen, Mandal

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 have been thinking about it because I have been thinking about it because I have been thinking about it. This is because I have been thinking about it because I have been thinking about it. This is because I have been thinking about it because

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

    - Filed Under⏎J ennifer Skaja has seen the signs of small miracles, as children with disabilities gain their voice through American Sign Language. Individuals with hearing impairment have⏎long used sign language to communicate, but studies

  2. #2 peak

    seven octopuses tested successfully learned the task and used the strategy more often once it was mastered.⏎It's only one example of clever tricks used by cephalopods. Check out our full-length feature to find out more about these animals'

  3. #3 peak

    language.⏎The Unified Modeling Language is an open method used to specify, visualise,⏎construct and document the artifacts

  4. #4 peak

    sequential'] fruit = ['raspberry', 'pomegranite', 'bananana', 'grape', 'loganberry'] print "You are an" , random.choice (verb) , random.choice (fruit)⏎Any Tutorial Videos

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. L7:212 excites
  2. L8:1254 suppresses
  3. L8:1926 weakly excites
  4. L8:1065 weakly suppresses
  5. L4:578 weakly suppresses
  6. L6:2770 weakly suppresses
  7. L4:680 weakly excites
  8. L8:2198 weakly excites
  9. L7:529 weakly suppresses
  10. L6:1498 weakly suppresses
  11. L6:799 weakly excites
  12. L8:1250 weakly suppresses
  13. L7:302 weakly suppresses
  14. L4:1287 weakly excites 'out' in 'turns out'
  15. L7:659 weakly excites
  16. L6:2490 weakly suppresses
  17. L6:2135 weakly excites
  18. L8:1798 weakly suppresses
  19. L7:2471 weakly excites
  20. L6:2334 weakly suppresses
  21. L3:1952 weakly excites
  22. L1:1923 weakly suppresses
  23. L0:827 weakly excites
  24. L6:2013 weakly suppresses

Feeds later layers

  1. L11:952 excites
  2. L10:1463 excites
  3. L11:1165 excites
  4. L11:2919 suppresses
  5. L17:1531 excites
  6. L10:1864 excites
  7. L10:2883 excites
  8. L10:1884 weakly suppresses
  9. L14:1034 weakly suppresses
  10. L24:2511 weakly suppresses
  11. L11:2406 weakly excites
  12. L20:2775 weakly suppresses
  13. L12:1249 weakly excites
  14. L16:2108 weakly suppresses
  15. L14:458 weakly excites
  16. L12:1226 weakly excites
  17. L11:1061 weakly suppresses
  18. L10:877 weakly excites
  19. L24:974 weakly excites
  20. L20:2492 weakly suppresses
  21. L15:2026 weakly suppresses
  22. L10:2637 weakly excites evaluative words: good, bad, positive
  23. L19:2952 weakly excites
  24. L14:2205 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 -2.46 and -2.351 values between -2.12 and -2.011 values between -1.89 and -1.783 values between -1.67 and -1.552 values between -1.55 and -1.443 values between -1.44 and -1.334 values between -1.33 and -1.2110 values between -1.21 and -1.1013 values between -1.10 and -0.9816 values between -0.98 and -0.8718 values between -0.87 and -0.7634 values between -0.76 and -0.6442 values between -0.64 and -0.5385 values between -0.53 and -0.42151 values between -0.42 and -0.30303 values between -0.30 and -0.19550 values between -0.19 and -0.071509 values between -0.07 and 0.04554 values between 0.04 and 0.15281 values between 0.15 and 0.27140 values between 0.27 and 0.3876 values between 0.38 and 0.5039 values between 0.50 and 0.6133 values between 0.61 and 0.7213 values between 0.72 and 0.849 values between 0.84 and 0.957 values between 0.95 and 1.064 values between 1.06 and 1.182 values between 1.18 and 1.292 values between 1.29 and 1.411 values between 1.41 and 1.521 values between 1.97 and 2.09offnegativepositiveoften

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. agara
  2. grade
  3. kost
  4. ffield
  5. grade
  6. temperament
  7. ieber
  8. każdego
  9. atorial
  10. easing

Suppresses

  1. WithPath
  2. 的位置
  3. positions
  4. enqu
  5. lez
  6. mitt
  7. 位置
  8. locations
  9. ataires
  10. `_