Neuron Explorer

Qwen3-0.6B

'in' after belief verbs

A neuron in layer 2 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 'in' when it follows verbs of belief, like 'believe in', 'believed in' or 'believing in'. When it was turned up, the model's text did not clearly change in a related way.

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 season of failure is the best time for sowing the seeds of success.⏎27. I don’t believe in failure. It’s not failure if you enjoyed the process.⏎28. I

  2. #2 peak

    to grow only if they could evolve some way of using citrate. Lenski expected to see evolution in action. This was an appropriate expectation for one who believes in evolution, because bacteria reproduce quickly and can have huge populations, as in this case

  3. #3 peak

    their own research projects<|endoftext|>Victicrat (vik'ti krat) n. (victim + -crat) 1) a supporter of the mentality believing in perpetual victimhood, who blames his or her plight on other person(s), event

  4. #4 peak

    which also included the "music of the spheres" (the sound that no doubt had to be produced by the planets encircling earth).⏎Pythagoras believed in reincarnation and claimed to remember previous incarnations. [Transmigration of souls is

  5. #5 peak

    were with Mary and saw it happen, finally believed on him.” (TLB)⏎Jesus delayed on purpose so God’s glory would be shown and others would believe in him.⏎Sometimes Jesus does the same with our requests, doesn’t he?⏎He

  6. #6 peak

    this was another opportunity for people to believe in him.⏎By the time they arrived in Bethany, Lazarus had been in

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 thinking about myself. I have been thinking about you. I have been thinking about some people. I have been thinking about my own things. I have been thinking about you. I have been thinking about myself. I have been

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

    ’s take a minute to rewind a little and discuss what RA is. Rheumatoid Arthritis is an autoimmune disorder in which your body mistakenly begins attacking the synovium as though they were an invading illness. The synovium is a lining

  2. #2 peak

    up to 150 years, and the biggest Gartrap ever found was the size of a human-sized breastplate.⏎OOC-Thank you ScorpianJinx for the name of “Gartrap”.<|endoftext|>Although it is a lot

  3. #3 peak

    rate even if you gain the weight again.⏎How much energy you use at any point in your life actually varies depending on if you’ve ever been heavier or skinnier.⏎Thoughts: From an evolutionary standpoint, this is all amazing. The

  4. #4 peak

    rd anniversary of a West Chicago Charity Minstrel Show, the high school’s Glee Club will perform a twoact program of songs, dances, and skits performed in blackface and featuring the popular songs, “Old Man River”, “

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. L1:1973 weakly suppresses
  2. L1:1910 weakly excites
  3. L0:178 weakly suppresses
  4. L0:1301 weakly suppresses
  5. L1:92 weakly excites
  6. L0:3030 weakly excites
  7. L1:718 weakly suppresses
  8. L1:739 weakly excites
  9. L0:2881 weakly suppresses
  10. L0:1 weakly suppresses
  11. L0:1708 weakly suppresses
  12. L1:2819 weakly suppresses
  13. L0:527 weakly excites
  14. L0:1286 weakly suppresses
  15. L1:1784 weakly suppresses
  16. L0:1224 weakly suppresses
  17. L1:1099 weakly excites
  18. L1:388 weakly suppresses
  19. L0:2534 weakly excites
  20. L0:510 weakly excites
  21. L1:526 weakly suppresses
  22. L1:2891 weakly suppresses
  23. L1:1513 weakly suppresses
  24. L1:1340 weakly suppresses

Feeds later layers

  1. L4:2970 weakly suppresses
  2. L13:2366 weakly suppresses
  3. L4:2772 weakly suppresses
  4. L4:582 weakly excites
  5. L3:714 weakly suppresses
  6. L18:195 weakly excites
  7. L8:598 weakly excites
  8. L7:2414 weakly suppresses
  9. L15:180 weakly excites
  10. L3:532 weakly suppresses
  11. L4:833 weakly suppresses
  12. L12:281 weakly excites
  13. L10:2489 weakly suppresses
  14. L3:2986 weakly suppresses
  15. L8:1830 weakly suppresses
  16. L24:2178 weakly excites
  17. L13:1435 weakly excites
  18. L19:2306 weakly excites
  19. L4:1079 weakly excites
  20. L9:1768 weakly suppresses
  21. L13:834 weakly excites
  22. L15:2148 weakly suppresses
  23. L16:1416 weakly excites
  24. L8:1428 weakly suppresses 'on' introducing a location or surface

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.

2 values between -1.24 and -1.123 values between -0.65 and -0.542 values between -0.54 and -0.4222 values between -0.42 and -0.30159 values between -0.30 and -0.18852 values between -0.18 and -0.062126 values between -0.06 and 0.05566 values between 0.05 and 0.17133 values between 0.17 and 0.2920 values between 0.29 and 0.416 values between 0.41 and 0.525 values between 0.52 and 0.642 values between 0.64 and 0.762 values between 0.76 and 0.881 values between 0.88 and 1.001 values between 1.00 and 1.111 values between 1.11 and 1.231 values between 1.23 and 1.351 values between 1.58 and 1.701 values between 1.70 and 1.821 values between 1.94 and 2.051 values between 3.35 and 3.47offnegativepositiveoften

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. aut
  2. direct
  3. McKenzie
  4. arks
  5. True
  6. direct
  7. pat
  8. thon
  9. (dc
  10. Aut

Suppresses

  1. 经历
  2. 經歷
  3. 佩服
  4. hiba
  5. 扮演
  6. ガー
  7. 习惯了
  8. experienced
  9. ScreenState
  10. 经历了