Neuron Explorer

Qwen3-0.6B

'the' in 'hit in the body part' idioms

A neuron in layer 12 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 the word 'the' in phrases like 'shot in the head', 'hit him in the back' or 'pat on the back', where a body part is about to be named. Turning it up did not produce any obvious theme in the generated text.

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

    Thomas, by Caravaggio (Michelangelo Merisi da, 1571–1610) which shows Thomas literally poking Jesus in the side to feel his wounds.⏎Pretty gross. It also depicts two other disciples looking

  2. #2 peak

    and Eighth circuits have all said, in so many words, no right exists to have a machine gun. You can add the U.S. Court of Appeals for the Ninth Circuit to the list.⏎In affirming the conviction of Alaskan Matthew Wayne

  3. #3 peak

    have the option of joining the expedition for two weeks.⏎HOW WILL YOU HELP⏎You<|endoftext|>Adding and formatting mathematical equations in your papers can be a real pain in the neck. This is especially the case with complicated expressions involving matrices, calculus, bin

  4. #4 peak

    in a railroad station, before shooting a second time.⏎One bullet only grazed Garfield’s shoulder but the other one, the fatal one, hit him in the back missing his spinal cord although it passed the first lumbar vertebra and lodged

  5. #5 peak

    his high school bathroom and shot himself in the head.⏎Megan Meier, 13, committed suicide after being harassed

  6. #6 peak

    Wentworth to Lyme.⏎- Louisa jumps off the Cobb steps and knocks herself unconscious on the ground.⏎- Captain Wentworth carries Louisa to the Harvilles’ home.⏎- The doctor says that Louisa will recover, but cannot be

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 want to be in the job, and I want to be in the role that I have been in is something that I want to be in is something that I have been in is something that I want to be in is something that 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

    into a robot.⏎“They didn’t actually know they could build it themselves,” said Santanna Lea, program director at the Ed Endres Boys & Girls Club.⏎She conceded she didn’t know much about robotics at the

  2. #2 peak

    engineering of plant clock systems, with powerful applications to agriculture.⏎(PRWeb UK) March 17, 2010 -- Researchers at the RIKEN Plant Science Center have clarified the function of three proteins that play a central role in

  3. #3 peak

    a teacher helped her students learn over the course of the year. Here are the facts that correct common misconceptions about the tool.<|endoftext|>Researchers at the RIKEN Plant Science Center have clarified the function of three proteins that play a central role in

  4. #4 peak

    for their male love interests.Continue Reading⏎The Sadie Hawkins tradition comes from the comic strip Li'l Abner in which women chase men around

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. L10:120 strongly suppresses
  2. L10:1377 strongly suppresses
  3. L11:1168 strongly excites
  4. L9:662 strongly suppresses
  5. L10:321 strongly suppresses
  6. L10:1644 strongly excites
  7. L4:73 strongly suppresses
  8. L9:142 strongly excites
  9. L9:227 excites
  10. L9:2661 excites
  11. L3:344 excites
  12. L2:205 excites
  13. L1:740 suppresses
  14. L9:2198 excites
  15. L2:1439 excites
  16. L5:705 excites
  17. L3:299 excites
  18. L11:875 suppresses
  19. L10:365 suppresses
  20. L5:493 excites
  21. L5:153 suppresses
  22. L10:1162 excites
  23. L3:2559 suppresses
  24. L9:24 excites "the" before a named organisation or title

Feeds later layers

  1. L13:1698 strongly suppresses
  2. L14:826 suppresses
  3. L15:702 excites
  4. L14:343 excites
  5. L16:391 excites
  6. L15:309 excites
  7. L14:547 suppresses
  8. L19:1579 suppresses
  9. L14:2965 suppresses
  10. L19:2198 suppresses
  11. L16:1497 suppresses
  12. L19:2555 suppresses
  13. L17:1238 suppresses
  14. L15:668 suppresses
  15. L14:298 excites
  16. L13:906 suppresses
  17. L13:2727 suppresses
  18. L16:1715 suppresses
  19. L13:2634 suppresses
  20. L18:1770 suppresses
  21. L13:1365 suppresses
  22. L18:1326 suppresses
  23. L15:1645 suppresses
  24. L16:1643 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 -3.12 and -2.974 values between -2.82 and -2.681 values between -2.53 and -2.386 values between -1.79 and -1.642 values between -1.64 and -1.503 values between -1.50 and -1.354 values between -1.35 and -1.204 values between -1.20 and -1.055 values between -1.05 and -0.918 values between -0.91 and -0.7614 values between -0.76 and -0.6114 values between -0.61 and -0.4752 values between -0.47 and -0.32327 values between -0.32 and -0.171195 values between -0.17 and -0.021690 values between -0.02 and 0.13407 values between 0.13 and 0.2789 values between 0.27 and 0.4233 values between 0.42 and 0.5718 values between 0.57 and 0.7110 values between 0.71 and 0.864 values between 0.86 and 1.014 values between 1.01 and 1.161 values between 1.16 and 1.301 values between 1.30 and 1.454 values between 1.45 and 1.604 values between 1.60 and 1.751 values between 1.89 and 2.041 values between 2.04 and 2.191 values between 2.63 and 2.78offnegativepositiveoften

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. ках
  2. ,
  3. otland
  4. 新娘
  5. ,在
  6. ,默认
  7. thern
  8. аз
  9. 。
  10. oints

Suppresses

  1. -www
  2. aspect
  3. viso
  4. elevator
  5. 的身影
  6. utivo
  7. 身影
  8. 栏
  9. ería
  10. ibase