Neuron Explorer

Qwen3-0.6B

"for" introducing a purpose or source

A neuron in layer 6 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 lights up on the word "for" when it links a thing to what it is for, sought from, or meant for, such as "looking to English sources for portraiture" or "turning to animals for food". Steering it up or down did not produce a clear change in the writing.

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

    as in his other works of the time, the artist employed formulaic poses, gestures, and dress, a result, in part, of looking to English sources for portraiture, but also a means of meeting the many requests for commissions.

  2. #2 peak

    . (See Speed Force Powers section.) However, the Speed Force is not the source from which other DC characters with super speed such as Superman or Captain Marvel derive their powers.⏎Writer John Byrne maintained modest abilities for the speedster character Danny Hilltop

  3. #3 peak

    do prey on other animals. And, now, as their traditional food sources are becoming more scarce because of human development, Dingoes are turning to domesticated animals for food, pitting themselves against the sheep farmers.⏎“Quite often they’ll go

  4. #4 peak

    0)⏎See Corbett (2000:173) for languages where mass nouns take plural rather⏎than singular morphology (and a few languages

  5. #5 peak

    vital so that you have a timing grid where you can follow the notes as they pass. Refer to the sheet ‘Reading Music: The Very Basics - Examples’ for some simple lines to get all this information working for you.⏎For now, when

  6. #6 peak

    nitrogen deficiency (yellowing leaves) and respond with quick side-dressings of a nitrogen-rich fertilizer such as fish emulsion. Contact your local County Extension office for controls of common corn pests such as corn earworms and European corn borers

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: the fact that the community is the first to the sun, and the second to the sun. In the first row, I have 1, 2, 3, and 4, and the second to the sun. If 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

    Cochinos, these projects would not have been possible without Anthony Ives. A former San Francisco stock trader who at one point was managing 50 billion dollars for the state of California, Ives found his way to Honduras after Sept.

  2. #2 peak

    Labor Statistics.⏎The Census Bureau, which tracks annual wages, found women who worked full-time, year-round in 2010 made 77 cents for every dollar men earned across the country. This comparison includes all male and female workers

  3. #3 peak

    the days of rest, some slaves would hold quilting bees, with both men and women. It was also sometimes tradition that slaves could keep the money they earned for the sale of goods during the holiday.⏎While the holiday season was meant to be

  4. #4 peak

    Gray Otis House⏎There are three houses named the Harrison Gray Otis House in Boston, Massachusetts. All were built by noted American architect Charles Bulfinch for the same man, Harrison Gray Otis.-First Harrison Gray Otis House:

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. L5:1090 excites
  2. L4:963 weakly excites
  3. L1:1578 weakly suppresses
  4. L3:381 weakly excites 'for' in research institute names
  5. L5:3026 weakly excites
  6. L5:1308 weakly suppresses
  7. L4:1709 weakly suppresses
  8. L5:50 weakly excites
  9. L3:2843 weakly excites
  10. L3:1631 weakly suppresses
  11. L1:789 weakly suppresses
  12. L2:75 weakly suppresses
  13. L1:2479 weakly suppresses
  14. L3:1711 weakly suppresses comma inside large numbers
  15. L3:2567 weakly excites
  16. L4:1222 weakly suppresses
  17. L5:2022 weakly suppresses
  18. L4:2718 weakly excites
  19. L2:2820 weakly excites
  20. L5:2841 weakly excites
  21. L1:2008 weakly suppresses
  22. L4:2265 weakly suppresses
  23. L1:1860 weakly suppresses
  24. L0:2521 weakly suppresses

Feeds later layers

  1. L15:1386 suppresses prepositions after passive verbs
  2. L9:654 suppresses
  3. L14:1547 excites
  4. L14:1192 suppresses
  5. L9:2390 suppresses
  6. L8:2715 excites
  7. L12:2276 excites
  8. L12:2756 excites "of" after a noun of quantity or container
  9. L10:2278 suppresses
  10. L9:1571 weakly excites
  11. L12:1916 weakly excites
  12. L9:2267 weakly suppresses 'with' after exchange nouns
  13. L15:2207 weakly suppresses
  14. L7:428 weakly excites
  15. L17:2197 weakly suppresses
  16. L7:1579 weakly suppresses
  17. L8:447 weakly excites
  18. L16:1877 weakly excites
  19. L7:14 weakly suppresses
  20. L15:2225 weakly excites
  21. L11:361 weakly suppresses
  22. L12:1642 weakly excites
  23. L9:1562 weakly suppresses 'by' before a byline or agent
  24. L19:544 weakly 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 -2.68 and -2.501 values between -1.62 and -1.453 values between -1.45 and -1.271 values between -1.27 and -1.103 values between -1.10 and -0.921 values between -0.92 and -0.755 values between -0.75 and -0.5730 values between -0.57 and -0.40219 values between -0.40 and -0.221244 values between -0.22 and -0.051929 values between -0.05 and 0.13420 values between 0.13 and 0.3139 values between 0.31 and 0.484 values between 0.48 and 0.664 values between 0.66 and 0.831 values between 2.06 and 2.241 values between 2.59 and 2.761 values between 2.76 and 2.941 values between 4.16 and 4.34offnegativepositiveoften

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. 更多信息
  2. 筏
  3. EventArgs
  4. information
  5. salvation
  6. 机电
  7. 入党
  8. 的信息
  9. 收益
  10. 解答

Suppresses

  1. tsy
  2. strar
  3. ь
  4. embro
  5. theast
  6. ント
  7. umpy
  8. ROUP
  9. actory
  10. aha