Neuron Explorer

Qwen3-0.6B

'one' before 'of' in 'is one of the'

A neuron in layer 16 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 'one' when it comes right before 'of the most...' or a similar phrase, as in 'it is one of the best'. When it was turned up, the model's writing drifted into odd repetition and loose, rambling sentences rather than anything about this idea.

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

    reef fish abundance and distribution trends between locations. Armed with the knowledge of where<|endoftext|>Edited by William Byron Forbush This is a book that will never die — one of the great English classics. . .

  2. #2 peak

    200m photos are uploaded to Facebook each day. These three “v”s neatly encapsulate the reasons why we are experiencing a data explosion, one that is resulting

  3. #3 peak

    great with yogurt or cereal.⏎2. Eggplant. These beautiful purple veggies are one of the best dietary sources of antioxidants and also provide lots of soluble fiber. Try

  4. #4 peak

    layout of our collection is much more light, airy and spacious. Following on from Education, I’ve been taking a fresh look at the History section.⏎It’s one of the most extensive in terms of the number of publications. All kinds of stories

  5. #5 peak

    or a weight belt. These muscles, one on each side, are your true core muscles and strengthening them will give you power

  6. #6 peak

    how Buddha nature produces the conditions for Buddha nature.”⏎There is much said and written about “Buddha nature”. Maybe to much. In my experience it is one of the most misunderstood terms that has arisen from Buddhism moving to the West. I

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 have been, for example, the first, for the first, but not only for the first, but not only for the first, for the first, for the first. I have no one, no, no, no, no

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

    Report on Macdonald (Undersea Features) (Wunderman, R., ed.). Bulletin of the Global Volcanism Network, 32:1. Smithsonian Institution. https://doi.org/10.5479

  2. #2 peak

    urchasing Power Parity Exchange Rates for the Global Poor,"⏎American Economic Journal: Applied Economics,⏎American Economic Association, vol. 3(2), pages 137-66, April.⏎- Angus Deaton & Olivier Duprie

  3. #3 peak

    ak Dun v. Yukon, 2015 YKCA 18 (the “appeal decision”), the Yukon Court of Appeal unanimously allowed

  4. #4 peak

    ; Magnuson, Terry (2013). "A novel selection marker for efficient DNA cloning and recombineering in E. coli". PLoS ONE 8 (2): e57075. . . http://

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. L3:244 strongly suppresses
  2. L4:961 strongly excites
  3. L10:848 suppresses
  4. L3:1810 excites
  5. L0:871 excites
  6. L11:1852 excites the digit 1 in numbers
  7. L4:247 suppresses
  8. L10:1639 suppresses
  9. L2:1829 suppresses
  10. L5:559 suppresses
  11. L10:1284 excites
  12. L10:2268 excites
  13. L9:1373 weakly suppresses
  14. L8:972 weakly excites
  15. L0:1500 weakly suppresses
  16. L11:2056 weakly excites the digit zero inside numbers and times
  17. L0:2393 weakly excites
  18. L0:1332 weakly suppresses
  19. L10:800 weakly excites
  20. L2:2029 weakly suppresses
  21. L0:2471 weakly suppresses
  22. L10:1602 weakly excites the number 1 as a unit value
  23. L10:722 weakly suppresses
  24. L6:1502 weakly suppresses

Feeds later layers

  1. L21:518 excites
  2. L19:720 excites
  3. L18:2608 excites
  4. L22:260 excites
  5. L23:2466 excites
  6. L23:794 excites
  7. L19:1251 excites
  8. L19:2118 excites
  9. L22:1081 excites
  10. L17:1056 suppresses
  11. L19:2221 suppresses
  12. L21:442 suppresses
  13. L25:1220 excites
  14. L19:288 suppresses
  15. L26:2856 excites
  16. L19:1331 excites
  17. L17:3022 excites
  18. L24:489 weakly excites
  19. L18:1686 weakly excites
  20. L17:963 weakly suppresses
  21. L25:2583 weakly excites
  22. L17:2705 weakly excites 'of' in 'one of the' phrases
  23. L19:1752 weakly excites
  24. L23:1563 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.

588 values between -1.53 and -0.643269 values between -0.64 and 0.2516 values between 0.25 and 1.143 values between 1.14 and 2.037 values between 2.03 and 2.921 values between 2.92 and 3.811 values between 3.81 and 4.713 values between 4.71 and 5.602 values between 6.49 and 7.381 values between 7.38 and 8.272 values between 8.27 and 9.161 values between 10.05 and 10.941 values between 13.61 and 14.502 values between 15.39 and 16.281 values between 16.28 and 17.171 values between 19.85 and 20.742 values between 23.41 and 24.302 values between 24.30 and 25.191 values between 25.19 and 26.081 values between 27.86 and 28.752 values between 29.64 and 30.531 values between 33.20 and 34.09offnegativepositiveoften

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. ploy
  2. ển
  3. Thousand
  4. 趸
  5. 被打
  6. onn
  7. culator
  8. //**⏎
  9. liter
  10. -shot

Suppresses

  1. strings
  2. scr
  3. 率
  4. sar
  5. rats
  6. walls
  7. 率为
  8. labels
  9. ulous
  10. istas