Neuron Explorer

Qwen3-0.6B

capital 'K' starting a name piece

A neuron in layer 27 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 responds to a capital K that begins a name or word piece, such as the K in Kaliangara or Koguryo. Its steering results do not show a clear theme, so what it does for the text is unclear.

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

    presentation at the conference, Jeff Schinske, professor of biology at De Anza Community College, and three current or former students — Amanda Snyder, Jahana Kaliangara, and Monica Cardenas — described an intervention designed to enhance students

  2. #2 peak

    culture towards Japan. In the year 660 it was conquered by Silla 6, which in 668, with the capitulation of Koguryŏ, was able, for the first time in history, to unify

  3. #3 peak

    Science Identity in a Diverse, Community College Context⏎Jeff Schinske, Amanda Snyder, Heather Perkins, Mary Wyner, Monica Cardenas, Jahana Kaliangara—all of De Anza College⏎De Anza Community College,

  4. #4 peak

    |View the image Gallery|⏎Flowing out of the mountains surrounding the Native community of Kake, Gunnuk Creek meanders through this seaside town and on into Keku Strait. The creek provides fresh water for the municipality and the water supply

  5. #5 peak

    (Bhavanasunya). Manu starts getting involved in various emotions, thoughts and actions. These are sequentially portrayed with Shraddha, Ida, Kilaat and other characters playing their part, contributing in them. The chapters are

  6. #6 peak

    associated with multiple sclerosis⏎Science | January 13, 2022⏎Bjornevik K, Cortese M, Healy BC, Kuhle J, Mina MJ, Leng Y, Elledge SJ,

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: Even while naturally good naturally good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good good

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

    of events.”⏎The new normal⏎“This analysis confirms what we already know – that we are suffering an extreme weather event caused by climate change,” says Gareth Redmond-King, a climate change specialist at WWF. “

  2. #2 peak

    only. Though<|endoftext|>نوع مقاله : مقاله پژوهشی⏎1 دانشیار معماری، دانشکده معماری و شهرسازی، دانشگاه علم

  3. #3 peak

    .⏎2 پژوهشگر دوره تخصصی دکتری معماری منظر، دانشکده معماری و شهرسازی، دانشگاه علم

  4. #4 peak

    children vaccinated against COVID-19.⏎In an opinion piece for The Hill, Senator Roger Marshall (R-Kan.) says COVID-19 immune response research is important, as well as

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. L22:2170 strongly excites
  2. L21:590 excites
  3. L18:816 suppresses
  4. L20:613 suppresses
  5. L26:495 suppresses
  6. L19:381 excites word-start 'acc' fragments
  7. L20:265 weakly excites
  8. L25:2286 weakly excites
  9. L18:569 weakly excites
  10. L22:56 weakly suppresses comma after a clause opener
  11. L20:1120 weakly excites
  12. L20:582 weakly excites
  13. L4:1860 weakly excites
  14. L20:61 weakly suppresses
  15. L16:7 weakly excites
  16. L20:2297 weakly excites
  17. L0:2999 weakly suppresses
  18. L10:1795 weakly suppresses
  19. L0:2385 weakly suppresses
  20. L16:61 weakly excites
  21. L17:1216 weakly suppresses
  22. L0:1996 weakly excites
  23. L19:2402 weakly excites
  24. L16:74 weakly suppresses

Feeds later layers

None: this is the last layer.

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 -42.38 and -37.472 values between -17.84 and -12.941 values between -12.94 and -8.034 values between -8.03 and -3.133886 values between -3.13 and 1.785 values between 1.78 and 6.694 values between 6.69 and 11.592 values between 11.59 and 16.501 values between 41.03 and 45.941 values between 124.44 and 129.341 values between 148.97 and 153.88offnegativepositiveoften

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. 很高
  2. 感染者
  3. .retrieve
  4. terior
  5. comed
  6. 素
  7. ieval
  8. ::$
  9. 很差
  10. 很低

Suppresses

  1. umar
  2. огда
  3. han
  4. おく
  5. mor
  6. irk
  7. 本身就
  8. aiser
  9. -priced
  10. cing