Neuron Explorer

Qwen3-0.6B

words after 'what' and 'go through' in speech

A neuron in layer 6 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 small words that come right after a verb or 'what', such as 'through' in 'go through' or the 's and 're in 'what it's' and 'what you're'. It is most active in casual, spoken-style sentences. Its negative side, on words like 'says' after a person or group, is a different pattern.

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 events of that tragic year of 1941, but our memory should not allow us to forget what the Soviet people had to go through in those blood-filled years of 1941-1945

  2. #2 peak

    ."⏎- “Godfather doesn't like being told what to do by the enemy.”⏎- “Godfather needs an airfield.”⏎Mark wanted to know what it’s called when someone talks like this. And he wondered if he was alone in thinking

  3. #3 peak

    of the ovaries in a woman is a natural process that every female has to go through at some point in her life. By medical standards, this time is fixed during

  4. #4 peak

    whatsoever. It's completely dark. That is what we're looking for and that is what makes this area so incredibly special."⏎The Namib

  5. #5 peak

    ’ve heard this word many times over the last few years, but unless you have actually participated in a detoxification program, you probably don’t really understand what it’s all about. Given the somewhat controversial nature of this topic, as well as the

  6. #6 peak

    lived in. That was the social contract before the New Deal. There was no Medicaid for the poor, no subsidized housing or home mortgage interest deduction, no unemployment insurance, no Social Security for the disabled or the elderly. Life was nasty, brut

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 problem of a couple. So, for the first time, I have been thinking about the problem. What is the answer to the question: "What is the sum of the two numbers 3 and 2? Let me know 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

    and positive psychology is impacting the behavior of more than 70 boys with serious behavioral or criminal issues.⏎Salekin and his team have developed a system that he says has been more effective at reaching troubled youth at the facility than typical methods, like

  2. #2 peak

    tide laps across them, back and forth, every day.”⏎One set of markings came from a two-legged, meat-eating dinosaur that researchers say was about the size of a car. They say its footprints have three toes

  3. #3 peak

    a book or looking it up on a webpage. In particular – I will be focusing on the Romans and the Greeks as these are especially interesting, and in my opinion, more factual. We can learn a lot from visiting sites, but we can

  4. #4 peak

    to a debate that we are likely to have in the coming decade, a debate about how we know the past and how we look at the written record that I suspect will be of interest to literary scholars and historians alike. It is a philosophical debate

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. L5:2622 weakly excites
  2. L5:1030 weakly excites
  3. L4:2187 weakly excites
  4. L2:627 weakly suppresses
  5. L1:2605 weakly excites
  6. L5:1463 weakly excites
  7. L4:179 weakly suppresses
  8. L4:1870 weakly excites
  9. L4:929 weakly excites
  10. L5:657 weakly excites
  11. L0:1371 weakly excites
  12. L4:2564 weakly suppresses
  13. L3:265 weakly suppresses
  14. L0:1847 weakly excites
  15. L4:153 weakly excites
  16. L4:19 weakly suppresses
  17. L2:2402 weakly excites
  18. L5:198 weakly excites unclear: weak "and" in lists
  19. L4:118 weakly excites
  20. L5:1495 weakly excites
  21. L3:3 weakly suppresses
  22. L1:2328 weakly suppresses
  23. L1:1590 weakly suppresses
  24. L5:619 weakly suppresses

Feeds later layers

  1. L17:1192 suppresses
  2. L8:2127 suppresses
  3. L7:2601 suppresses
  4. L15:566 suppresses
  5. L8:1847 suppresses
  6. L18:2153 weakly suppresses
  7. L12:2966 weakly excites
  8. L8:507 weakly suppresses
  9. L8:502 weakly suppresses
  10. L14:752 weakly suppresses
  11. L17:1756 weakly suppresses
  12. L15:452 weakly suppresses
  13. L11:2106 weakly suppresses
  14. L8:2822 weakly suppresses
  15. L14:647 weakly suppresses
  16. L7:357 weakly suppresses
  17. L14:1124 weakly suppresses
  18. L23:1196 weakly excites
  19. L21:2408 weakly suppresses
  20. L19:640 weakly excites
  21. L21:496 weakly suppresses
  22. L14:500 weakly suppresses
  23. L12:2063 weakly suppresses
  24. L16:2315 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 -3.20 and -3.081 values between -2.85 and -2.731 values between -2.50 and -2.381 values between -2.03 and -1.921 values between -1.80 and -1.681 values between -1.68 and -1.572 values between -1.33 and -1.222 values between -1.10 and -0.982 values between -0.87 and -0.756 values between -0.75 and -0.635 values between -0.63 and -0.5222 values between -0.52 and -0.4083 values between -0.40 and -0.28315 values between -0.28 and -0.17933 values between -0.17 and -0.051822 values between -0.05 and 0.07493 values between 0.07 and 0.18138 values between 0.18 and 0.3038 values between 0.30 and 0.4220 values between 0.42 and 0.5313 values between 0.53 and 0.652 values between 0.65 and 0.773 values between 0.77 and 0.881 values between 1.12 and 1.232 values between 1.35 and 1.47offnegativepositiveoften

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. 庥
  2. <%=
  3. ��
  4. <?=
  5. %;">⏎
  6. %;⏎
  7. -<?
  8. <?=
  9. "><?
  10. Altern

Suppresses

  1. obuf
  2. gebn
  3. elocity
  4. iske
  5. 体育彩票
  6. olut
  7. ynomials
  8. وسط
  9. pository
  10. urname