Neuron Explorer

Qwen3-0.6B

'wide' in 'a wide range of'

A neuron in layer 16 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 'wide' in phrases like 'a wide range' or 'a wide variety', and on 'hundreds' in 'hundreds of studies'. It turns off on words like 'sooner' in 'sooner or later'. Turning it up did not produce text that clearly showed this idea.

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

    a Safe Hospital?⏎When we prevent healthcare workers from facing a wide range of hazards on the job, including needle stick injuries, back injuries, latex

  2. #2 peak

    well as the symptoms and treatments associated with them⏎Understanding the Types of Broken Bones⏎The characteristics of broken bones can vary greatly. This means that there’s a wide range of

  3. #3 peak

    is increasing with each year. Unfortunately, a lot of that may include television shows, movies, video games, or YouTube videos that include violence.⏎There have been hundreds of research studies examining the effects of television violence on children and teenagers. The results

  4. #4 peak

    Grass Valley garden. Singer’s extensive experience gardening in the Sierra foothills provided the basis to formulate lists of plants deer avoid in our local growing areas.⏎Whether our wide-eyed friends devour prized roses or scrape the bark off new trees, deer can indeed

  5. #5 peak

    to type with hands-on advice for identifying the mystery interlopers in your borders, and information about their height, spread, flowering period and toxicity. Discover a wide array of British garden plants, with practical tips for their care and

  6. #6 peak

    10% flavan<|endoftext|>The eyes are the windows to the soul, or so goes the proverb. As humans, we use our eyes to express a wide variety of emotions, often without even realizing we’re doing

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 question to the next level (QNT]S] is to ask the question that is a question of * * * * * * * * * * * * * * * * * * * * * * * * *

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

    worth considering at this time because, sooner or later, similar fights will break out in other areas. In the U.S

  2. #2 peak

    and made by consensus. They appreciate the discussion itself<|endoftext|>How to Unzip .tgz File Using the Terminal?⏎If you are using open-source packages, then sooner or later, you will encounter the .tgz or .tar.gz files.

  3. #3 peak

    1920 further asks the year of naturalization. Indirectly,⏎the 1820 and 1830 census provide a clue with the question "number of⏎foreigners in each household not naturalized."⏎

  4. #4 peak

    education. It was pointed out that boundaries and divisions are necessary to make sense of the complex world we live

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. L15:1587 strongly excites
  2. L15:1900 strongly suppresses
  3. L15:1404 strongly suppresses
  4. L15:792 strongly suppresses
  5. L15:381 strongly excites
  6. L15:435 strongly excites
  7. L15:1616 strongly excites word fragments mid-word
  8. L15:1135 strongly suppresses
  9. L15:222 strongly excites
  10. L15:201 strongly excites
  11. L15:451 strongly excites
  12. L15:787 strongly excites
  13. L15:2803 strongly suppresses
  14. L15:1164 strongly excites
  15. L15:12 suppresses
  16. L14:126 excites
  17. L14:1090 excites
  18. L15:966 suppresses
  19. L14:169 excites
  20. L15:1043 suppresses
  21. L14:871 excites
  22. L15:1300 excites
  23. L15:992 excites
  24. L15:227 excites

Feeds later layers

  1. L18:2208 excites
  2. L19:1258 excites
  3. L22:849 suppresses
  4. L20:1163 excites
  5. L22:2961 excites
  6. L27:1731 suppresses
  7. L19:2839 suppresses
  8. L18:123 suppresses
  9. L26:154 excites
  10. L19:2889 weakly suppresses
  11. L26:1775 weakly suppresses
  12. L26:2854 weakly excites
  13. L20:2805 weakly suppresses
  14. L17:1971 weakly excites
  15. L19:1070 weakly suppresses
  16. L26:1430 weakly suppresses
  17. L26:192 weakly excites
  18. L26:1266 weakly suppresses
  19. L18:866 weakly suppresses
  20. L26:104 weakly suppresses
  21. L21:2548 weakly excites
  22. L26:2560 weakly excites
  23. L26:1979 weakly excites
  24. L26:2635 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 -6.71 and -6.302 values between -6.30 and -5.891 values between -5.89 and -5.482 values between -5.48 and -5.084 values between -5.08 and -4.6711 values between -4.67 and -4.2611 values between -4.26 and -3.8519 values between -3.85 and -3.4427 values between -3.44 and -3.0357 values between -3.03 and -2.6368 values between -2.63 and -2.2288 values between -2.22 and -1.81149 values between -1.81 and -1.40201 values between -1.40 and -0.99312 values between -0.99 and -0.59502 values between -0.59 and -0.18878 values between -0.18 and 0.23524 values between 0.23 and 0.64316 values between 0.64 and 1.05223 values between 1.05 and 1.46164 values between 1.46 and 1.86100 values between 1.86 and 2.2764 values between 2.27 and 2.6853 values between 2.68 and 3.0945 values between 3.09 and 3.5029 values between 3.50 and 3.9015 values between 3.90 and 4.3110 values between 4.31 and 4.7210 values between 4.72 and 5.137 values between 5.13 and 5.546 values between 5.54 and 5.942 values between 5.94 and 6.352 values between 6.35 and 6.762 values between 6.76 and 7.171 values between 7.17 and 7.581 values between 8.39 and 8.801 values between 9.21 and 9.62offnegativepositiveoften

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. лас
  2. בל
  3. Forbes
  4. Pruitt
  5. Clin
  6. kald
  7. oeff
  8. Freed
  9. ある
  10. 불구하고

Suppresses

  1. yx
  2. //**⏎
  3. y
  4. ism
  5. aat
  6. ioned
  7. qualifiers
  8. itives
  9. ivity
  10. !(: