Neuron Explorer

Qwen3-0.6B

capital 'R' starting a word

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 fires on a capital 'R' that starts a new word, especially at the beginning of a line or paragraph, such as 'Ruler', 'Rifle', 'Rogers' or 'Rosh'. It is pushed the other way by a capital R inside a longer term, like 'Rake' in a list. Turning it up produced repeated words, which tells us little about the letter.

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

    can help us see how the function and responsibility of "Elders" has mutated over the years into something very different from its original form.⏎1. 'Ruler' (prostatis; noun form) 'Rule' (proist

  2. #2 peak

    Monoflex bullet.⏎Bullet diameter: .458 inch.⏎Bullet weight: 250 grains.⏎Bullet ballistic coefficient: .175.⏎Rifle zero: 135 yards, 2″ mid-range rise.⏎

  3. #3 peak

    serves as special assistant to the president and executive director of the White House Office of Faith-based and Neighborhood Partnerships, also published a reflection on Religious Freedom Day.⏎Rogers celebrates the Religious Land Use and Institutionalized Persons Act, which passed Congress

  4. #4 peak

    spp.) — muscadine⏎Greenbriar (smilax spp.)⏎Pokeweed (poke salad) —a forb or herbaceous plant⏎R<|endoftext|>While Blackboard is the dominant commercial learning management (LMS) for the

  5. #5 peak

    Rural Fire Service (RFS), and the community to decrease the risk of bushfire to people, property and the environment.<|endoftext|>by Ruth M. Green⏎RUF Lehigh Summer Conference 2004⏎A. Taken from Deborah

  6. #6 peak

    .uk/2015/08/rav-lichtenstein-zl.html⏎Your comment will be posted after it is approved.⏎Leave a Reply.⏎R

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: everyone who lives in public buildings public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public public

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

    be used when cutting hard work pieces such as high hardness steel, where tool bit strength is required. See the differences between positive shape and negative shape below.⏎- Rake angle = Positive⏎- Rake surface (back side of tool

  2. #2 peak

    This article explains basic knowledge about rake angle and introduces the latest technology used to take accurate rake angle measurements.⏎- Rake Angle⏎- Positive and Negative Rake Angle in End Milling⏎-

  3. #3 peak

    eth not at all. '⏎AKAI HEIRLOOM RICE - GRAIN AKAI RICE is a heirloom rice-grain from Camargue, France.⏎Ahead

  4. #4 peak

    The angle it forms with the workpiece is called the relief angle. This is the angle required for avoiding interference between the tool and workpiece.⏎Positive and Negative Rake

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. L22:961 strongly suppresses
  2. L20:257 suppresses
  3. L2:19 suppresses
  4. L17:253 suppresses
  5. L10:1473 suppresses
  6. L18:331 suppresses
  7. L17:420 suppresses
  8. L23:1368 excites
  9. L26:721 excites
  10. L0:1365 suppresses
  11. L19:572 excites
  12. L19:683 excites
  13. L7:922 excites
  14. L16:113 weakly excites
  15. L18:343 weakly suppresses
  16. L26:434 weakly suppresses
  17. L2:1866 weakly suppresses
  18. L2:493 weakly suppresses
  19. L10:273 weakly suppresses
  20. L5:3019 weakly excites
  21. L7:286 weakly excites
  22. L16:2477 weakly excites
  23. L4:1923 weakly suppresses
  24. L18:1077 weakly excites

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 -22.44 and -21.171 values between -13.58 and -12.321 values between -11.05 and -9.791 values between -9.79 and -8.524 values between -3.46 and -2.1915 values between -2.19 and -0.933671 values between -0.93 and 0.34207 values between 0.34 and 1.605 values between 1.60 and 2.871 values between 5.40 and 6.661 values between 26.91 and 28.17offnegativepositiveoften

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. pewnością
  2. 世
  3. Provid
  4. >Title
  5. ücken
  6. 还是会
  7. iders
  8. aday
  9. wand
  10. i

Suppresses

  1. 違反
  2. 被执行
  3. 遇
  4. rowsing
  5. ��
  6. general
  7. 吓得
  8. 心疼
  9. 惊
  10. 该县