Neuron Explorer

Qwen3-0.6B

opening bracket after a term or number

A neuron in layer 14 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 an opening bracket that comes right after a name, abbreviation, or measurement, where the text is about to give the short form or the converted value, like '2 kg (4.4 lb)'. Turning it up led to repetitive or off-topic text, which does not tell us much.

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

    . The U.S. military was also developing miniature UAVs that could be launched and operated by one person. The Marine Corps began testing a 2-kg (4.4-l

  2. #2 peak

    God) and the charming Temple of Baalshamin (god of fertility) — and a monumental arch that opens onto a 1,200-meter (3,937 ft.) long colonnade, the center of this

  3. #3 peak

    and study noctilucent - or 'night shining' - clouds, odd collections of ice crystals that form near the edge of space some 50 miles (80 kilometers) above Earth's polar regions. The clouds form so high above

  4. #4 peak

    that was more or less inevitable. It bothers me that people are so stupid as to use this stuff .”⏎By contrast, synthetic tetrahydrocannabinol (THC) is available as dronabinol (Marinol) and

  5. #5 peak

    Zionist journalism.⏎Already a member? Login here.<|endoftext|>The fractured rock surfaces were observed under different loading stages in creep shear by making use of computerized tomography (CT). Through the creep shear tests, the failure modes of the fractured rocks have

  6. #6 peak

    and the belief that we can recover from setbacks and learn from them.⏎Singaporean students have typically scored very well in the Organisation for Economic Co-operation and Development’s (OECD) Programme for International Student Assessment (PISA) in Reading, Mathematics

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: this is the time to think about the place of the place (the place is not here and this is the place). So these are these things are not the place (so those are the place). So these are these things are not the

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

    said that the image of Marx has been imprinted in his heart since he was a child, adding that “Marx molded by a Chinese artist contains emotion and [warmth].”<|endoftext|>Citadel of Herat⏎This citadel, which

  2. #2 peak

    biologist at the University of Arizona in Tucson.⏎"They had no idea what it ate. But perhaps they knew that jumping spiders were cat-like in their movements, and [they] decided to name the spider after the agile panther Bagheera in

  3. #3 peak

    assigned to eastern Chad to provide guidence to a literacy program.⏎“The reason that I’m back in Africa is because I left a piece of my heart here and [now] I’m here to get it back,” Eunice Kua said

  4. #4 peak

    which is really useful for us, because if you have the animals behave in the same way all the time, there’s no room for flexibility in the face of [climate] change.”⏎Even with a colony containing hundreds of

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. L10:1459 suppresses
  2. L9:1065 suppresses
  3. L9:2010 suppresses
  4. L12:1443 excites opening parenthesis after a name or term
  5. L11:2774 weakly excites 'least' in 'at least' hedges
  6. L1:964 weakly excites "of" in "some kind of" or "some type of"
  7. L13:2302 weakly suppresses
  8. L1:1178 weakly excites
  9. L11:228 weakly excites
  10. L8:354 weakly excites opening parenthesis before a citation year
  11. L10:1643 weakly suppresses
  12. L6:990 weakly excites
  13. L0:1846 weakly excites
  14. L11:1077 weakly excites
  15. L2:981 weakly excites
  16. L10:1484 weakly suppresses
  17. L10:271 weakly excites
  18. L9:1421 weakly suppresses
  19. L5:330 weakly excites opening parenthesis after a noun
  20. L7:1590 weakly suppresses
  21. L13:553 weakly suppresses
  22. L8:2127 weakly excites
  23. L11:356 weakly suppresses
  24. L9:1899 weakly suppresses

Feeds later layers

  1. L15:1501 excites "and" joining two parts of a name or phrase
  2. L15:3004 excites
  3. L15:2831 excites
  4. L15:2437 excites opening parenthesis after a noun
  5. L15:1162 excites
  6. L15:734 excites
  7. L17:1679 excites
  8. L17:1214 excites
  9. L16:2049 excites
  10. L16:2201 excites
  11. L16:2289 excites 'or' linking two alternatives
  12. L16:882 excites
  13. L18:1386 excites unclear: words before 'and' or 'or'
  14. L15:232 excites
  15. L15:2215 weakly excites
  16. L15:3041 weakly excites
  17. L18:2136 weakly excites
  18. L17:2017 weakly excites
  19. L15:2884 weakly excites
  20. L16:247 weakly excites
  21. L15:2143 weakly excites
  22. L15:1380 weakly excites
  23. L15:1718 weakly suppresses
  24. L16:1074 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 -1.90 and -1.751 values between -1.44 and -1.292 values between -1.29 and -1.144 values between -1.14 and -0.992 values between -0.99 and -0.849 values between -0.84 and -0.6811 values between -0.68 and -0.5328 values between -0.53 and -0.38133 values between -0.38 and -0.23764 values between -0.23 and -0.082159 values between -0.08 and 0.08583 values between 0.08 and 0.23115 values between 0.23 and 0.3835 values between 0.38 and 0.5315 values between 0.53 and 0.6812 values between 0.68 and 0.8413 values between 0.84 and 0.992 values between 0.99 and 1.142 values between 1.14 and 1.291 values between 1.29 and 1.441 values between 1.44 and 1.601 values between 1.60 and 1.752 values between 1.75 and 1.901 values between 1.90 and 2.051 values between 2.05 and 2.204 values between 2.20 and 2.362 values between 2.51 and 2.661 values between 2.66 and 2.811 values between 2.96 and 3.121 values between 3.42 and 3.571 values between 4.03 and 4.18offnegativepositiveoften

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. rogen
  2. ,
  3. nearly
  4. frame
  5. rarian
  6. REW
  7. resp
  8. /
  9. чив
  10. 党组书记

Suppresses

  1. 为中国
  2. initely
  3. |[
  4. Ǻ
  5. 时代中国
  6. istically
  7. [B
  8. ⽤
  9. locals
  10. Bahamas