Neuron Explorer

Qwen3-0.6B

hedges like 'it turns out' and 'if any'

A neuron in layer 18 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 the word that finishes a small set phrase, such as 'turns out', 'if any', 'if possible' or 'would say'. Turned up, it nudged the model toward wordy, qualified sentences, though the effect was mixed and sometimes just repeated a word.

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

    that lights up when we see a baby or romantic partner, as well as the brain area stimulated by money, food, or sex. Giving, as it turns out, may offer as big a reward to the giver as to the receiver.⏎Giving

  2. #2 peak

    minimum wage.⏎Eighty-seven percent of single parent households are headed by women and of those 37% are in poverty (Association for Women’s Rights and Development).

  3. #3 peak

    Why don't you be the first to send us one?⏎If Google Street View is available, the image is from the best available vantage point looking, if possible, towards the location of the monument. Where it is not available, the satellite

  4. #4 peak

    look at how animation on the Internet came to its present (and very cool) state. It pretty much all started with gifs…⏎.gif files are, it turns out, older than I am by about two years. They were introduced in 1

  5. #5 peak

    also been an alarming increase in reports of anti-trans murders and other violence especially those perpetrated against younger American transwomen of color. However, there are few, if any, reports of anti-gay or anti-trans violence perpetrated against visitors.⏎There are many

  6. #6 peak

    , "Why, now is this seemingly obscure story from the Book of Genesis not only included in the Book of Ruth, but included in what is, in my contention, the climax of the entire Book?"⏎The passage Iím referring to is a

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, the, author, in,,,ressressressressressressressressressressressressressressressressressressressressressressressressressressressressressressressressressressressressressress

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

    weeks of learning online, which is open to all. The course format allows users to learn at their own pace, also engaging with others taking the course if they choose. There are no exams or assessments.⏎“It was an extraordinary experience to be the

  2. #2 peak

    puritan society. In his novel,The Scarlet Letter, Nath<|endoftext|>What they learned after only seven years is worth remembering (or learning, as the case may be).⏎The United States has operated under two constitutions. The first, The Articles

  3. #3 peak

    No approach. Meier was surprised by the assumption that non-marital sex has negative psychological consequences. The physical risks — unwanted pregnancy or sexually transmitted diseases, for example — were obvious.

  4. #4 peak

    general informational purposes only and is not a substitute for professional medical advice.⏎If you think you may have a medical emergency, call your doctor or (in the United States) 911 immediately. Always seek the advice of your doctor before starting

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. L16:650 strongly excites
  2. L15:1159 strongly excites ampersand in citation author lists
  3. L16:2905 strongly suppresses
  4. L15:2506 strongly suppresses
  5. L15:841 strongly suppresses
  6. L16:2626 strongly excites
  7. L15:2666 strongly excites
  8. L14:2932 strongly excites
  9. L17:207 strongly excites
  10. L15:2961 strongly suppresses
  11. L16:1788 excites
  12. L16:331 suppresses
  13. L16:2571 suppresses
  14. L15:2201 suppresses
  15. L15:3010 excites
  16. L17:1668 excites
  17. L16:3060 suppresses
  18. L17:1299 excites
  19. L15:2235 suppresses
  20. L17:975 suppresses
  21. L17:449 excites
  22. L17:1829 excites
  23. L16:2360 suppresses
  24. L17:260 suppresses commas mid-sentence before a continuation

Feeds later layers

  1. L19:845 strongly suppresses
  2. L21:344 strongly suppresses
  3. L24:572 strongly suppresses
  4. L19:682 strongly suppresses
  5. L26:236 strongly suppresses
  6. L27:86 excites
  7. L20:276 suppresses
  8. L20:756 suppresses
  9. L20:173 suppresses
  10. L27:286 suppresses
  11. L21:1070 suppresses
  12. L20:82 excites
  13. L25:438 suppresses
  14. L20:1083 suppresses
  15. L26:22 excites the 'res' fragment inside words
  16. L19:1130 suppresses
  17. L19:1201 suppresses
  18. L24:642 suppresses
  19. L24:6 excites
  20. L19:1468 suppresses
  21. L20:132 suppresses
  22. L21:301 suppresses
  23. L23:49 suppresses
  24. L24:304 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.

2 values between -3.78 and -3.431 values between -3.43 and -3.081 values between -3.08 and -2.737 values between -2.73 and -2.385 values between -2.38 and -2.036 values between -2.03 and -1.6816 values between -1.68 and -1.3436 values between -1.34 and -0.99104 values between -0.99 and -0.64228 values between -0.64 and -0.291990 values between -0.29 and 0.06950 values between 0.06 and 0.41227 values between 0.41 and 0.76102 values between 0.76 and 1.1068 values between 1.10 and 1.4546 values between 1.45 and 1.8026 values between 1.80 and 2.1517 values between 2.15 and 2.5014 values between 2.50 and 2.8514 values between 2.85 and 3.198 values between 3.19 and 3.549 values between 3.54 and 3.895 values between 3.89 and 4.244 values between 4.24 and 4.591 values between 4.59 and 4.943 values between 4.94 and 5.295 values between 5.29 and 5.632 values between 5.98 and 6.332 values between 6.33 and 6.682 values between 7.03 and 7.383 values between 7.38 and 7.731 values between 7.73 and 8.071 values between 8.07 and 8.422 values between 9.82 and 10.16offnegativepositiveoften

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. ANTED
  2. หาย
  3. licos
  4. agrams
  5. otive
  6. ulares
  7. encias
  8. ilian
  9. 柯
  10. caled

Suppresses

  1. ,
  2. ,"⏎
  3. .,
  4. .",
  5. **,
  6. [],
  7. !,
  8. ,
  9. ,",
  10. ",