Neuron Explorer

Qwen3-0.6B

"in" after a superlative or ordinal

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 "in" when it follows a superlative or "second," "only" or "last" noun, as in "the second in a series" or "the only life in the Universe." It is quiet on sentence-opening "In," which triggers its negative side. Turning it up pushed the model into repeated group and idea phrases.

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

    ately I have been reading a biography on John D. Rockefeller and wanted to share some of my insights.⏎John D. Rockefeller was one of the most successful businessmen in American history owning 1.5% of U.S. GDP in 1

  2. #2 peak

    Reference Count: N/A⏎Hand in Hand. Skills Activities for Tutors and Students.⏎Biles, James J.; And Others⏎The guide is the second in a two-volume series designed to provide volunteer tutors of English as a Second Language (

  3. #3 peak

    22 November 2021 | Vibhav peri | Crises⏎The Great Slaty Woodpecker, once the largest woodpecker in India, is now the largest woodpecker in the world.⏎This is because

  4. #4 peak

    scientists have made a surprising discovery: a gigantic aquifer of relatively fresh water trapped in porous sediments lying below the salty ocean.⏎A new book, the second in a series of primers with the Earth Institute imprint, provides an interdisciplinary overview drought

  5. #5 peak

    biology and is the longest-running citizen survey in the world.⏎The Matagorda County Mad Island Marsh Christmas Bird Count (CBC) is one of the most successful in the country every year and is typically the reigning champion when it comes to number of

  6. #6 peak

    continental unease between South America and Europe.⏎It led to several big football nations missing out on the tournament.⏎The third World Cup turned out to be the last in the pre-World War II era. The world had to wait 12

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 don't know what time of the year I want to have my own life. I think I have to choose my own life, which I have been in the world, since the other time of the year, which I have been.

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

    , messages, and information like recipes or instructions. In many cases, content like photos or videos is shared. Read on to hear more

  2. #2 peak

    , it not only affects the productivity of teams, but it can also potentially hurt relationships with customers or damage the reputation of the business.⏎How dirty data happens⏎In Salesforce and most other CRMs, the origin of dirty data can usually be pinpoint

  3. #3 peak

    changed between Commit 1 and Commit 3.⏎The diff will compare the differences between the two commits, showing what files were added, deleted, or modified.⏎In this example, Commit 1 is the baseline. You may also notice how the

  4. #4 peak

    wastewater lagoons across the state.⏎It would fail to remove harmful bacteria that impair streams and cause human illnesses, including dysentery and hepatitis A. In that case, even streams that gained new protection wouldn't see an improvement in water quality

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. L4:289 strongly excites
  2. L10:262 suppresses
  3. L14:1389 suppresses
  4. L8:351 suppresses 'in' after 'high' or 'dressed'
  5. L9:1025 excites
  6. L15:871 suppresses
  7. L3:493 suppresses
  8. L1:1179 suppresses 'in' after 'result' (results in)
  9. L14:1625 excites the word 'in' after a noun
  10. L5:490 excites
  11. L6:3070 suppresses
  12. L3:311 suppresses
  13. L4:1966 suppresses
  14. L7:2192 weakly excites
  15. L15:1328 weakly suppresses
  16. L1:1922 weakly suppresses
  17. L2:2307 weakly excites
  18. L11:1781 weakly excites
  19. L15:1468 weakly excites
  20. L5:729 weakly suppresses
  21. L4:1406 weakly excites
  22. L15:1642 weakly excites
  23. L3:1116 weakly excites
  24. L9:2862 weakly suppresses

Feeds later layers

  1. L17:2877 suppresses
  2. L19:1354 suppresses
  3. L23:967 suppresses
  4. L21:1935 suppresses
  5. L17:2126 weakly suppresses
  6. L17:505 weakly excites
  7. L19:1910 weakly suppresses
  8. L18:2904 weakly excites
  9. L18:2012 weakly suppresses
  10. L17:2314 weakly suppresses
  11. L25:2083 weakly excites
  12. L17:1574 weakly suppresses
  13. L24:893 weakly excites
  14. L20:2692 weakly excites
  15. L18:726 weakly excites
  16. L23:465 weakly suppresses
  17. L24:2584 weakly suppresses 'in' in set phrases like 'in mind'
  18. L25:2459 weakly excites
  19. L22:938 weakly suppresses
  20. L17:1562 weakly excites
  21. L17:718 weakly excites
  22. L17:2114 weakly excites
  23. L17:3069 weakly excites
  24. L19:1733 weakly suppresses

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.

3 values between -10.42 and -10.001 values between -9.17 and -8.752 values between -8.75 and -8.332 values between -7.91 and -7.491 values between -7.07 and -6.651 values between -4.14 and -3.724 values between -3.72 and -3.301 values between -3.30 and -2.884 values between -2.88 and -2.466 values between -2.46 and -2.044 values between -2.04 and -1.6216 values between -1.62 and -1.2024 values between -1.20 and -0.78145 values between -0.78 and -0.372548 values between -0.37 and 0.05992 values between 0.05 and 0.4782 values between 0.47 and 0.8928 values between 0.89 and 1.3117 values between 1.31 and 1.738 values between 1.73 and 2.153 values between 2.15 and 2.574 values between 2.57 and 2.992 values between 2.99 and 3.413 values between 3.41 and 3.832 values between 3.83 and 4.252 values between 4.66 and 5.081 values between 5.50 and 5.922 values between 5.92 and 6.34offnegativepositiveoften

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. aviours
  2. facts
  3. 夤
  4. Aggregate
  5. уществ
  6. lies
  7. idot
  8. aggregates
  9. Reads
  10. angement

Suppresses

  1. 没有必要
  2. atorial
  3. 收到了
  4. oping
  5. xic
  6. =view
  7. 没必要
  8. 直播间
  9. vh
  10. zew