Neuron Explorer

Qwen3-0.6B

'of' after amount or level nouns

A neuron in layer 5 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 word 'of' after nouns of quantity or degree, like 'amount of', 'levels of' or 'numbers of'. The signal is fairly weak, and turning it up or down did not clearly change the written text.

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

    Celsius, and preferably 1.5 degrees Celsius, from pre-industrial levels. The aim is to use the best available scientific data to reduce the global amount of greenhouse gases, mainly carbon dioxide and methane emissions, in the Earth’s atmosphere.⏎

  2. #2 peak

    utable to this, the forest officials can not only restrict tribal and forest dwellers from accessing forest lands and produce but can also punish the whole community for the act of an individual.⏎Into the bargain, the government has gone a step further and shifted

  3. #3 peak

    , all the social and medical developments we’ve achieve thus far haven’t tackled the TB problem in its roots. Scandinavian countries have been able to dramatically decrease the numbers of people getting ill with TB long before antibiotic treatment existed, thanks to improvements in housing

  4. #4 peak

    bi-products such as saw dust and planer shavings. This production demanded large amounts of water, and thus the pump tower and a water line was established. Both pump

  5. #5 peak

    31 products tested in the study, at least three-quarters of waterproof mascaras, two-thirds of foundations and over half of eye and lip products had high amounts of fluorine. All 29 products that were tested for PFAS after showing

  6. #6 peak

    These lipids consist of ceramides, fatty acids and cholesterol that help to hold in water and prevent dryness. People with dry skin often have lower levels of ceramides. This affects the skin’s ability to retain moisture. When 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: a long way, and then a 1. So, the website will be built from that. The problem is that the website is going to be built from that, and then the next part is going to be built from that. The

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

    1,000 striking plantation workers.⏎In 1959, rock-and-roll stars Buddy Holly, Ritchie Valens and J.P. "The Big Bopper" Richardson died in a small plane crash near Clear Lake,

  2. #2 peak

    the digital humanities. Through careful explanations of the field, examinations of terminology and themes, and illustrated case studies of diverse texts—from the Cyrus cylinder to the Eagles' "Hotel California"—Elaine Treharne and Claude Willan offer a clear

  3. #3 peak

    the Art and the Future Glossary References Author index Subject index About the Author.⏎(source: Nielsen Book Data)⏎'The fourth edition of Uwe Flick's "Introduction to Qualitative Research" remains the most comprehensive and thorough text in qualitative research

  4. #4 peak

    To access this title, visit your library in the app or on the desktop website.⏎Chronicles of the imagination Geographical⏎- Walta Evans "School Librarian"<|endoftext|>Wing Tsun or Wing Chun?⏎or Wing Chung

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. L1:606 weakly suppresses
  2. L3:2860 weakly excites
  3. L4:1081 weakly suppresses
  4. L0:32 weakly suppresses
  5. L2:2057 weakly suppresses
  6. L4:2199 weakly suppresses
  7. L4:781 weakly suppresses
  8. L4:982 weakly excites
  9. L0:1965 weakly excites
  10. L3:1372 weakly suppresses
  11. L4:1998 weakly suppresses
  12. L4:1373 weakly excites
  13. L4:207 weakly suppresses
  14. L4:2415 weakly excites
  15. L4:2230 weakly suppresses
  16. L4:1835 weakly suppresses
  17. L4:2565 weakly suppresses
  18. L4:2190 weakly excites
  19. L1:1069 weakly excites
  20. L3:601 weakly suppresses
  21. L1:1222 weakly suppresses
  22. L2:1355 weakly excites "about" in "what about" questions
  23. L4:635 weakly suppresses
  24. L3:2540 weakly excites

Feeds later layers

  1. L23:2092 weakly excites
  2. L6:2259 weakly excites
  3. L24:1722 weakly excites
  4. L22:2743 weakly excites
  5. L6:2909 weakly suppresses
  6. L15:1354 weakly excites
  7. L7:601 weakly suppresses
  8. L20:2306 weakly excites
  9. L9:1934 weakly suppresses
  10. L24:1363 weakly excites
  11. L7:921 weakly excites
  12. L17:64 weakly suppresses
  13. L18:960 weakly excites
  14. L12:2245 weakly excites
  15. L18:1429 weakly suppresses
  16. L10:472 weakly suppresses
  17. L7:1684 weakly excites
  18. L14:555 weakly suppresses
  19. L20:2461 weakly excites
  20. L15:2627 weakly excites
  21. L23:2020 weakly excites
  22. L10:2586 weakly suppresses
  23. L25:1734 weakly excites
  24. L16:892 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 -3.79 and -3.661 values between -2.51 and -2.391 values between -2.39 and -2.261 values between -2.26 and -2.131 values between -2.00 and -1.882 values between -1.49 and -1.372 values between -1.37 and -1.243 values between -1.24 and -1.112 values between -1.11 and -0.982 values between -0.98 and -0.869 values between -0.86 and -0.737 values between -0.73 and -0.6021 values between -0.60 and -0.4826 values between -0.48 and -0.3592 values between -0.35 and -0.22360 values between -0.22 and -0.091989 values between -0.09 and 0.031016 values between 0.03 and 0.16287 values between 0.16 and 0.2956 values between 0.29 and 0.4214 values between 0.42 and 0.545 values between 0.54 and 0.674 values between 0.67 and 0.803 values between 0.80 and 0.931 values between 0.93 and 1.052 values between 1.18 and 1.31offnegativepositiveoften

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. ировки
  2. registry
  3. ак
  4. бу
  5. -outs
  6. ContentValues
  7. elling
  8. 승
  9. rus
  10. Smarty

Suppresses

  1. endet
  2. toughness
  3. ち
  4. aser
  5. �试
  6. itter
  7. offsetof
  8. primera
  9. ôte
  10. 提前