Neuron Explorer

Qwen3-0.6B

periods inside names and initials

A neuron in layer 10 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 dot in a person's middle initial, like the period in 'Gerald R. Ford' or 'Harold G. Moore'. When it was turned up, the writing drifted into rambling, unrelated text about topics like houses and family.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    Gerald R. Ford.⏎Transcript from the February 10, 1995 online interview with former President Gerald R. Ford.⏎Grades: PreK–K, 1–2,

  2. #2 peak

    “We Were Soldiers Once . . . And Young,” by Lt. Gen. Harold G. Moore and war correspondent Joseph Galloway. The 2002 movie

  3. #3 peak

    (828) 395-1307 fax (828) 286-8208⏎Charles P. Wiggins, Director of Library Services⏎Documentation Styles for Citing Resources⏎(

  4. #4 peak

    also ill-equipped and trained, had nearly 40,000.⏎Price left a small garrison at Lexington, which was overrun by Major Frank J. White’s First Squadron Prairie Scouts on the early morning of October 1

  5. #5 peak

    was founded in 1975 by conservative activists John Terry Dolan, Charles Black and Roger Stone, with help from Richard Viguerie and Thomas F. Ellis. The group got its

  6. #6 peak

    7:30 a.m. and again at 2:00 p.m. in rooms 393-396 of the Ernest N. Morial Convention Center. The session is designed for all hematologists who treat patients

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 can't wait for you to play the game of the same color." What is the probability of getting a certain number of points? The probability of a win or loss game, the same color. If I choose a number of points

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

    San Francisco Bay Area. Greater Eureka, one of California's major commercial fishing ports, is the location of the largest deep water port between San Francisco and Coos Bay, a stretch of about . The headquarters of both the Six Rivers National Forest

  2. #2 peak

    and pdf⏎- Tuesday, June 1, 2021 2:11:00 AM⏎- 1 comment⏎File Name: the death and life of the great lakes .zip⏎- Discussion questions for ‘

  3. #3 peak

    .codeguru.com/algorithms/factorial.shtml I don't happen to think that the code there

  4. #4 peak

    .⏎Word Origin Middle English (in legal<|endoftext|>Keywords: Sargent Mountain⏎Historical Items Showing 1 of 1 View All⏎Contributed by: Mount Desert Island Historical Society⏎Location: Northeast Harbor⏎Images taken by itinerant photographers

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. L9:1618 excites
  2. L8:2315 excites
  3. L9:1599 suppresses
  4. L6:1447 weakly suppresses
  5. L9:1689 weakly suppresses
  6. L8:878 weakly excites
  7. L9:1625 weakly excites
  8. L2:2328 weakly suppresses
  9. L3:1641 weakly excites
  10. L4:3002 weakly excites
  11. L9:1522 weakly excites
  12. L8:1675 weakly suppresses
  13. L0:1329 weakly suppresses
  14. L0:1224 weakly suppresses
  15. L2:2259 weakly excites
  16. L0:178 weakly suppresses
  17. L3:2496 weakly excites
  18. L5:2274 weakly suppresses
  19. L1:2673 weakly suppresses
  20. L3:2589 weakly excites
  21. L8:493 weakly suppresses
  22. L9:832 weakly excites
  23. L8:1063 weakly excites the word "genus" in taxonomy
  24. L3:785 weakly suppresses the word 'other' after 'each'

Feeds later layers

  1. L11:1780 excites
  2. L12:2254 excites
  3. L11:1672 weakly excites
  4. L12:1976 weakly excites
  5. L15:1629 weakly suppresses
  6. L21:1607 weakly suppresses
  7. L21:146 weakly excites
  8. L17:1702 weakly excites
  9. L23:3046 weakly excites
  10. L26:2933 weakly suppresses
  11. L18:999 weakly excites
  12. L15:654 weakly suppresses
  13. L11:2450 weakly excites
  14. L27:3007 weakly excites
  15. L24:168 weakly suppresses
  16. L21:283 weakly suppresses
  17. L15:1435 weakly suppresses
  18. L11:704 weakly excites
  19. L23:3054 weakly excites
  20. L13:3054 weakly excites
  21. L12:2664 weakly suppresses
  22. L13:2873 weakly suppresses
  23. L26:42 weakly suppresses
  24. L15:1739 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.

1 values between -0.65 and -0.5412 values between -0.54 and -0.4358 values between -0.43 and -0.31212 values between -0.31 and -0.20720 values between -0.20 and -0.091684 values between -0.09 and 0.03933 values between 0.03 and 0.14206 values between 0.14 and 0.2652 values between 0.26 and 0.3718 values between 0.37 and 0.485 values between 0.48 and 0.602 values between 0.60 and 0.712 values between 0.71 and 0.821 values between 1.16 and 1.281 values between 2.30 and 2.411 values between 3.78 and 3.89offnegativepositiveoften

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. ↑
  2. 眼光
  3. ien
  4. dir
  5. uild
  6. 四处
  7. tract
  8. eur
  9. 眼
  10. 纲

Suppresses

  1. 合一
  2. ystery
  3. lycer
  4. *)⏎
  5. setResult
  6. .scalajs
  7. schließen
  8. CallCheck
  9. "⏎⏎⏎
  10. 县政府