Neuron Explorer

Qwen3-0.6B

"of" after a noun in trademark and title phrases

A neuron in layer 11 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

Fires on the word "of" right after a noun, especially in set phrases like "trademarks of", "fear of" and "a final report of". Turning it up made the model produce looping, repeated text.

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

    Hunter and Nancy A. Moran, will publish their paper, "Bacteriophages Encode Factors Required for Protection in<|endoftext|>Social media can create 'fear of missing out'⏎CHARLESTON, W.Va. -- As the constant

  2. #2 peak

    more.⏎- Perfect for center activities, homework and filling downtime between lessons⏎- Build critical reading skills⏎- A great review for testing⏎- Answers on back of cards for easy self checking⏎Figurative Language Practice Cards provide an easy way

  3. #3 peak

    example, in the image shown below, the bottle’s cast shadow is clearly incongruous with the shape of the bottle (as is the shadow on this cover of Time Magazine). Such obvious errors in a shadow are easy to spot, but more

  4. #4 peak

    1995-2012 Healthwise, Incorporated. Healthwise, Healthwise for every health decision, and the Healthwise logo are trademarks of Healthwise, Incorporated.⏎Find out what women really need.⏎Most Popular Topics⏎

  5. #5 peak

    in language use outside the classroom; using oral histories to promote literacy skills; using the newspaper with ESL students; and preparing the student for employment. A final report of the project is appended to the guide. (MSE) (Adjunct ER

  6. #6 peak

    ⏎5 letter words⏎4 letter words⏎3 letter words⏎2 letter words⏎Images for ZEATINSLoading...⏎SCRABBLE is the registered trademark of Hasbro and J.W. Spear & Sons Limited. Our scrabble word finder

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 user, the community, and the school of the the school of the the school of the the school of the the school of the the school of the the school of the community, the government of the state, and the local government 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

    ⏎Teacher Evaluation to Enhance Professional Practice 2000 US$ 24.95 167 pages<|endoftext|>Gate is the national monument of India. Situated in the heart of New Delhi⏎, it was designed by

  2. #2 peak

    of Publication⏎Blanks, C. M. (1948). San Antonio the Inland Gate. Retrieved from https://digitalcommons.pvamu.edu/pvamu-theses/395<|endoftext|>The Top

  3. #3 peak

    Cell Cycle and Growth by Extracellular Cues, Fall 2012. (Massachusetts Institute of Technology: MIT OpenCourseWare), http://ocw.mit.edu (Accessed). License: Creative Commons BY-NC-SA<|endoftext|>Make

  4. #4 peak

    Ten Nieuport 80s went to Brazil in November 1918, where they were used by the Escola de Aviacao Militar at Campos dos Afonsos. Brazil also received a number of Nieuport

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. L9:1627 excites
  2. L10:2362 suppresses
  3. L3:315 excites 'of' after a noun phrase
  4. L8:2257 suppresses
  5. L5:363 excites
  6. L9:2717 excites
  7. L7:790 excites
  8. L9:2672 excites
  9. L9:2070 suppresses
  10. L4:1686 excites
  11. L8:1003 suppresses "the" or "of" before a noun phrase
  12. L9:2264 excites 'of' after superlatives and 'the X of'
  13. L8:968 excites
  14. L9:654 suppresses
  15. L10:352 suppresses
  16. L9:1266 weakly suppresses
  17. L5:91 weakly excites
  18. L10:299 weakly suppresses
  19. L2:852 weakly suppresses
  20. L10:669 weakly excites
  21. L6:1637 weakly excites
  22. L9:1550 weakly excites 'to' after 'matters' or 'means' phrases
  23. L9:1428 weakly excites
  24. L5:953 weakly suppresses

Feeds later layers

  1. L15:2633 suppresses
  2. L17:2267 suppresses
  3. L16:3007 suppresses
  4. L16:1096 suppresses
  5. L15:632 suppresses
  6. L12:850 excites
  7. L15:942 excites
  8. L14:2840 suppresses
  9. L12:1904 suppresses
  10. L16:2612 suppresses
  11. L14:1728 suppresses "of" after a numbered section or title
  12. L17:865 suppresses
  13. L16:2852 suppresses 'in' after a noun or participle
  14. L13:287 suppresses
  15. L16:961 suppresses
  16. L12:958 suppresses
  17. L12:1653 suppresses
  18. L18:183 excites
  19. L12:2535 suppresses
  20. L16:564 suppresses
  21. L14:1707 suppresses
  22. L12:2849 suppresses '-based' after a place name
  23. L13:844 suppresses 'of' after a percentage or share
  24. L16:1441 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.

2 values between -1.82 and -1.691 values between -1.69 and -1.572 values between -1.57 and -1.441 values between -1.44 and -1.311 values between -1.31 and -1.181 values between -1.18 and -1.052 values between -1.05 and -0.921 values between -0.92 and -0.796 values between -0.79 and -0.678 values between -0.67 and -0.5414 values between -0.54 and -0.4155 values between -0.41 and -0.28288 values between -0.28 and -0.151020 values between -0.15 and -0.021688 values between -0.02 and 0.11614 values between 0.11 and 0.24165 values between 0.24 and 0.3618 values between 0.36 and 0.498 values between 0.49 and 0.624 values between 0.62 and 0.752 values between 0.75 and 0.882 values between 1.01 and 1.142 values between 1.14 and 1.261 values between 1.26 and 1.391 values between 2.55 and 2.681 values between 3.19 and 3.32offnegativepositiveoften

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. אה
  2. tin
  3. vé
  4. arnings
  5. 石家
  6. Revenue
  7. érica
  8. ään
  9. -R
  10. żenia

Suppresses

  1. OfString
  2. of
  3. idual
  4. iculty
  5. utm
  6. of
  7. COPYRIGHT
  8. OF
  9. 场上
  10. ofday