Neuron Explorer

Qwen3-0.6B

names and titles inside proper nouns

A neuron in layer 16 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on the middle of a fixed name or title, such as 'Age' in 'An Age', 'Nation' in 'A Nation at Risk', or 'End' in 'The End of the Cold War'. It is quiet, or pushed negative, on phrases like 'Call Before You Dig' and 'All Others Are Silent'. Turning it up made the output repeat itself.

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

    . S. cabinet departments, including those overseeing commerce, education, energy, and labor (some of this material and references for it can be found in my An Age

  2. #2 peak

    approach to what is called "hands-on" science has been growing in recent years at all levels of education, since the 1983 report "A Nation at Risk" criticized public education, including science curriculums, in American

  3. #3 peak

    still honor the format of exploring hands-on activities, learning about artwork in our galleries, and making an inspired art project.⏎As always, Kid Quest is an at-your-own-pace art adventure. In this case, take all the time you

  4. #4 peak

    This video is part two of a seven-part National Academies series, Climate Change: Lines of Evidence. The video outlines, with the use of recent research and historical

  5. #5 peak

    68" onward, had little effect but to strengthen comparable hard-line views in the Kremlin.⏎Armstrong, David, and Erik Goldstein, eds. The End of the Cold War. Routledge, 2013.⏎

  6. #6 peak

    ), Part 4, Chapter 7, eBook.<|endoftext|>Transcript for A New Horizon, segment 05 of 13⏎The Eastern Colorado Project's

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 been, as... and I have been... and I have been... and I have been... and I have been... and I have been... and I have been... and I have been... and I have been... and I

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

    in the upper echelons. Richard would have probably received these treatments because he was a member of the nobility."<|endoftext|>When Leaders Speak… All Others Are Silent!⏎December 22, 2015 | 3 min read

  2. #2 peak

    From Tree Roots⏎- Locate sewer lines – You can call your local public works office or the national 811 “Call Before You Dig” number to locate underground utilities on your property. Before you do any kind of

  3. #3 peak

    . There were numerous reports of NYC residents unable to get their phone calls through on 9/11, because the system was jammed.⏎Business Before Pleasure on the Wire: Effect of ‘Phone Philandering on the Call Frequency Curve of

  4. #4 peak

    ving⏎Tier 2—Assessment and Problem Solving⏎We can no longer implement instruction we believe to be great and cross our fingers and hope for the best. We must identify appropriate strategies the way a physician determines an appropriate prescription. Then

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. L14:3049 suppresses
  2. L15:1395 suppresses
  3. L13:1531 suppresses
  4. L13:1550 suppresses
  5. L12:2126 suppresses
  6. L13:2938 excites
  7. L14:1631 excites
  8. L14:282 suppresses
  9. L7:2596 suppresses
  10. L8:1267 excites
  11. L15:2459 suppresses
  12. L7:2155 suppresses
  13. L15:1191 suppresses
  14. L4:881 excites
  15. L13:2983 weakly suppresses
  16. L15:354 weakly excites
  17. L12:1831 weakly excites
  18. L13:1742 weakly excites
  19. L4:1026 weakly suppresses
  20. L13:1945 weakly excites
  21. L15:484 weakly excites
  22. L11:2815 weakly suppresses
  23. L13:293 weakly excites
  24. L7:1356 weakly suppresses

Feeds later layers

  1. L17:76 excites
  2. L17:375 suppresses
  3. L20:353 suppresses
  4. L17:293 suppresses
  5. L17:112 suppresses
  6. L25:334 suppresses
  7. L24:121 suppresses
  8. L17:186 suppresses
  9. L20:320 suppresses
  10. L24:78 excites
  11. L17:181 excites
  12. L19:211 excites
  13. L19:1201 suppresses
  14. L17:48 suppresses
  15. L20:202 suppresses
  16. L20:218 suppresses
  17. L18:160 excites
  18. L20:34 excites
  19. L17:937 suppresses
  20. L18:1120 suppresses
  21. L23:40 suppresses
  22. L17:2075 suppresses
  23. L21:365 excites
  24. L18:360 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 -8.13 and -7.841 values between -4.46 and -4.181 values between -3.34 and -3.051 values between -3.05 and -2.772 values between -2.77 and -2.492 values between -2.49 and -2.213 values between -2.21 and -1.932 values between -1.93 and -1.645 values between -1.64 and -1.367 values between -1.36 and -1.0819 values between -1.08 and -0.8049 values between -0.80 and -0.52399 values between -0.52 and -0.242241 values between -0.24 and 0.051036 values between 0.05 and 0.3391 values between 0.33 and 0.6117 values between 0.61 and 0.8914 values between 0.89 and 1.179 values between 1.17 and 1.466 values between 1.46 and 1.741 values between 2.58 and 2.871 values between 2.87 and 3.15offnegativepositiveoften

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. ivial
  2. createAction
  3. …⏎⏎
  4. ixin
  5. omat
  6. omon
  7. 内外
  8. ون
  9. もの
  10. ait

Suppresses

  1. Slovak
  2. 즐
  3. 院院士
  4. !
  5. 佶
  6. iced
  7. .bill
  8. angelo
  9. ยาย
  10. _currency