Neuron Explorer

Qwen3-0.6B

middle of a fixed multi-word term

A neuron in layer 13 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 a word in the middle of a fixed name or term, such as "emerald ash borer", "weighted average cost of capital" or "foot-and-mouth disease". The pattern is loose, and steering did not reflect it.

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

    . E.g. I had gone to the shop and bought some chips.⏎Other examples include.⏎After she had read it from start to finish, Sophie ripped the letter in half.⏎The frog had jumped from the lilypad to the shore.⏎Tom

  2. #2 peak

    . People at risk include those whose occupations expose them to blood, such as health-care workers. The vaccine is now commonly given to all newborns.⏎• Hepatitis A vaccine: Hepatitis A is transmitted through contaminated food or water. The Hep

  3. #3 peak

    , provides goal writing guidance, especially useful for early intervention and children on the autistic spectrum disorder.<|endoftext|>The online WACC Calculator is used to calculate the weighted average cost of capital (WACC).⏎In finance, The weighted average cost of capital,

  4. #4 peak

    . Have some introduced species caused changes that most everyone would agree have been very harmful? Absolutely. By killing timber trees, gypsy moths and the emerald ash borer have caused, and continue to cause, enormous economic damage to the United

  5. #5 peak

    oofed animals. In 1981, Chile was officially declared FMD-free without vaccination, after complying with all international health requirements.⏎Foot-and-mouth disease (FMD) affects mainly swine and related wild ruminants and

  6. #6 peak

    complain to police in Karnataka online?⏎- What does an eagle with two heads mean?⏎- Did the Hittites invade Egypt?⏎- What does the word Hittite mean?⏎- Who were the Hittite gods?⏎- What did the

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 think it's important to make sure that the world is in your thoughts. I think it's a thing of making sure you are always making your thoughts, but I think there is a lot more to it. I think you are

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

    41–46); Samuel, the altar boy who became God’s prophet (1 Samuel 3:10–21); David, the shepherd boy who became king (1 Samuel 16); Esther, the teenage queen who

  2. #2 peak

    Library of Congress) (1890)⏎"To avoid these evils, each gathering hule has its "boot," a rounded hood of fire-clay which surrounds the hole on the inside

  3. #3 peak

    do you use the word Which?⏎- Who is example sentences?⏎- Why is it called crush?⏎Which means in a sentence?⏎He’s a politician now, which means that bragging and whoring his story is the job description.⏎The ech

  4. #4 peak

    istic methods uncover sophisticated meanings and monkey dialects⏎The same species of monkeys located in separate geographic regions use their alarm calls differently to warn of approaching predators, a linguistic analysis by a team of scientists reveals. The study, which appears in the journal

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. L11:1482 excites
  2. L11:1368 excites
  3. L12:2778 excites
  4. L12:1712 excites
  5. L11:1107 suppresses
  6. L11:1692 suppresses
  7. L11:1298 suppresses
  8. L12:1547 excites
  9. L12:1074 excites
  10. L11:722 excites
  11. L1:853 excites
  12. L11:888 suppresses
  13. L9:600 excites
  14. L12:1359 suppresses
  15. L11:442 weakly excites
  16. L9:1981 weakly excites
  17. L10:826 weakly excites
  18. L10:542 weakly excites word completing a technical term
  19. L10:198 weakly suppresses
  20. L12:114 weakly excites
  21. L11:284 weakly excites
  22. L12:685 weakly suppresses
  23. L2:742 weakly excites
  24. L12:1683 weakly suppresses

Feeds later layers

  1. L15:1769 strongly suppresses
  2. L14:2284 suppresses
  3. L14:331 suppresses
  4. L14:1860 excites
  5. L14:1603 excites
  6. L15:1502 suppresses
  7. L14:410 excites
  8. L16:1021 excites
  9. L16:1738 excites
  10. L16:2944 suppresses
  11. L14:369 suppresses
  12. L14:372 weakly excites
  13. L14:97 weakly excites
  14. L23:708 weakly suppresses
  15. L16:2438 weakly suppresses
  16. L14:336 weakly excites
  17. L14:2995 weakly excites
  18. L14:1113 weakly suppresses
  19. L14:644 weakly suppresses
  20. L15:359 weakly suppresses
  21. L17:1000 weakly excites
  22. L15:2044 weakly suppresses
  23. L14:654 weakly suppresses
  24. L16:2152 weakly excites

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 -1.23 and -1.152 values between -1.15 and -1.071 values between -1.07 and -0.991 values between -0.99 and -0.921 values between -0.92 and -0.842 values between -0.84 and -0.761 values between -0.76 and -0.694 values between -0.69 and -0.6113 values between -0.61 and -0.5329 values between -0.53 and -0.4665 values between -0.46 and -0.38138 values between -0.38 and -0.30270 values between -0.30 and -0.23442 values between -0.23 and -0.15622 values between -0.15 and -0.071041 values between -0.07 and 0.00683 values between 0.00 and 0.08265 values between 0.08 and 0.16116 values between 0.16 and 0.2362 values between 0.23 and 0.3135 values between 0.31 and 0.3935 values between 0.39 and 0.4619 values between 0.46 and 0.5413 values between 0.54 and 0.6217 values between 0.62 and 0.697 values between 0.69 and 0.775 values between 0.77 and 0.854 values between 0.85 and 0.923 values between 0.92 and 1.002 values between 1.00 and 1.082 values between 1.08 and 1.151 values between 1.15 and 1.231 values between 1.23 and 1.312 values between 1.31 and 1.381 values between 1.38 and 1.462 values between 1.77 and 1.84offnegativepositiveoften

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. moduleId
  2. Opens
  3. 不排除
  4. OUCH
  5. broad
  6. fry
  7. drifted
  8. hire
  9. ']+
  10. YLE

Suppresses

  1. �
  2. 年中国
  3. 变化
  4. .DrawString
  5. istan
  6. reco
  7. aling
  8. 手腕
  9. 等奖
  10. velle