Neuron Explorer

Qwen3-0.6B

'of' after a person's name

A neuron in layer 13 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' that comes right after a scientist's or author's name and introduces their institution, as in 'Michael Liu of the University of Hawaii'. It is quiet, or even pushed the other way, after country names like 'Republic of Yemen'. Turning it up produced repetitive text that does not show this clearly.

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

    brown dwarfs and much closer to those of giant exoplanets — it could even have water clouds in its atmosphere," the paper's lead author, Michael Liu of the University of Hawaii's Institute for Astronomy, said

  2. #2 peak

    from an ancient burial site on Crete, in a cave called Hagios Charalambos, a team led by archaeogeneticist Gunnar Neumann of the Max Planck Institute for Evolutionary Anthropology in Germany found genetic evidence of

  3. #3 peak

    4-Year Institutions⏎Shifting Students’ Stereotypes of Scientists to Enhance Science Identity in a Diverse, Community College Context⏎Jeff Schinske, Amanda Snyder, Heather Perkins, Mary Wyner, Monica Cardenas, Jahana

  4. #4 peak

    use this method to find out exactly what goes wrong in the nerve cells in movement disorders such as ataxias," said Prof. Dr. Stefan Herlitze (RUB Department for Biology and Biotechnology).⏎The researchers report is in the Journal

  5. #5 peak

    potential role of biomarkers in tracking neuronal recovery, which may be associated with duration of [return to sport],” wrote Cassandra L. Pattinson, PhD, of the University of Queensland, Brisbane, Australia, and the National Institutes of Health,

  6. #6 peak

    a has provoked alarm around the world, and there are no new classes of antibiotics in development.⏎In this week's Scrubbing Up column, Peter Greenhouse of the British Association for Sexual Health & HIV (BASHH) argues financial incentives will

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 a thought for the new year, and the new year is the year of the new data, and the new year is the year of the new data, and the new data, and the new data, and the new data

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

    declared independence and became known as the People's Democratic Republic of Yemen (South Yemen), which united with the North in 1990

  2. #2 peak

    is 884 with a serial no. of 00139⏎Kindly Donated by Callum Wilson.⏎With thanks to http://www.dvq.com/oldcomp/micros.htm for the original photograph without

  3. #3 peak

    1986, only 14 cases pertaining to blasphemy were reported.⏎By its constitution, the official name of Pakistan is the "Islamic Republic of Pakistan." More than 96% of Pakistan's 167 million

  4. #4 peak

    every human need. In Psalms we read, “Give thanks to the Lord, for he is good; his love endures forever. Let the redeemed of the Lord tell their story. . . . Let them give thanks to

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. L12:2348 excites
  2. L12:2314 excites
  3. L12:1817 excites
  4. L12:1768 suppresses
  5. L10:2362 suppresses
  6. L12:139 excites
  7. L12:2889 suppresses
  8. L12:1763 excites
  9. L11:2542 excites
  10. L9:2390 excites
  11. L8:1107 suppresses
  12. L9:1627 excites
  13. L11:1418 suppresses
  14. L12:2664 weakly suppresses
  15. L12:2810 weakly excites
  16. L11:1994 weakly excites
  17. L12:273 weakly excites
  18. L12:1673 weakly suppresses
  19. L12:2289 weakly excites 'of' after part-whole nouns
  20. L12:1794 weakly suppresses
  21. L12:2456 weakly excites
  22. L9:1961 weakly suppresses 'of' in titles and place names
  23. L12:1286 weakly suppresses
  24. L10:2529 weakly excites

Feeds later layers

  1. L17:2906 excites
  2. L16:2427 excites
  3. L19:2853 excites
  4. L18:1931 excites
  5. L17:978 excites
  6. L21:2846 excites 'at' after a job title, before an institution
  7. L17:3041 excites
  8. L16:1051 excites
  9. L17:604 excites
  10. L14:2038 weakly suppresses
  11. L15:1456 weakly excites
  12. L18:2349 weakly suppresses
  13. L14:1707 weakly excites
  14. L18:56 weakly excites
  15. L20:1038 weakly excites
  16. L19:817 weakly excites
  17. L14:1550 weakly excites
  18. L20:2623 weakly excites
  19. L22:2134 weakly excites
  20. L19:2135 weakly excites
  21. L19:1001 weakly excites "be" after will or you'll
  22. L20:862 weakly excites
  23. L16:2716 weakly excites
  24. L14:1893 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 -1.15 and -1.022 values between -1.02 and -0.891 values between -0.89 and -0.762 values between -0.76 and -0.643 values between -0.64 and -0.5113 values between -0.51 and -0.3852 values between -0.38 and -0.25200 values between -0.25 and -0.121128 values between -0.12 and 0.011489 values between 0.01 and 0.13699 values between 0.13 and 0.26224 values between 0.26 and 0.3962 values between 0.39 and 0.5210 values between 0.52 and 0.656 values between 0.65 and 0.783 values between 0.78 and 0.903 values between 1.03 and 1.161 values between 1.16 and 1.291 values between 1.29 and 1.422 values between 1.42 and 1.541 values between 1.54 and 1.672 values between 1.80 and 1.931 values between 1.93 and 2.061 values between 2.44 and 2.571 values between 3.85 and 3.98offnegativepositiveoften

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. .local
  2. USDA
  3. Cam
  4. 教育部
  5. _cam
  6. .microsoft
  7. 市教育局
  8. ording
  9. airs
  10. 局

Suppresses

  1. 通行证
  2. wort
  3. тиров
  4. akter
  5. 嬗
  6. 胡子
  7. hetics
  8. 瑁
  9. uell
  10. ANTI