Neuron Explorer

Qwen3-0.6B

'and' joining paired adverbs

A neuron in layer 9 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

The neuron fires on the word 'and' when it joins two adverbs or action words, like 'easily and quickly' or 'freely and uncontrollably'. It is negative on the '-ly' ending of an adverb. Turning it up gave repetitive or off-topic text, so that result does not help explain it.

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

    eyes and ears” that check food from other countries to make sure they’re safe.⏎- Improving the traceability of foods so that their origins can be easily and quickly traced and identified in the event of a recall.⏎- Allowing the FDA

  2. #2 peak

    personal vow never to be like their parent.⏎The venter style is at the opposite end of the anger management continuum. Unlike the suppressor, this person freely and uncontrollably expresses their anger. They take no prisoners and have no mercy in

  3. #3 peak

    in infamy, the United States of America was suddenly and deliberately attacked by naval and air forces of the Empire of Japan,” said President Franklin

  4. #4 peak

    of view, no more than 10 meters away. Even in the dark, I immediately recognized the shape of a large female brown bear. As I slowly and quietly backed away, two cubs ran up the bank and onto the road where

  5. #5 peak

    skills without any emphasis on creating a piece of art. Children are, by nature, process oriented. Adults are, by nature, product oriented. Adults can easily and unknowingly shift the focus of art activities to creating an end product. As adults

  6. #6 peak

    383 stated:⏎"Except as otherwise required by statute, matters of official record shall be made available, in accordance with published rule, to persons properly and directly concerned, except information held confidential for

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 want to be a teacher in a small town. I have a lot of students and I think the town is small. I have a 1200-1800. I think the best teacher in the country,

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

    , laced with methane and various hydrocarbons – and since the arrival of the Cassini spacecraft in July 2004 it has only grudgingly surrendered its secrets.⏎Titan’s northern hemisphere was in the dead of winter when Cass

  2. #2 peak

    Alzheimer's disease, Parkinson's disease, diabetes, heart disease, multiple sclerosis, Lou Gehrig's disease, severe burns, and many more illnesses and injuries, literally allowing the body to heal itself. These amazing cells can come from many sources besides

  3. #3 peak

    whole poem, but we're just getting into it now, thirty-nine lines in. Lowell illustrates how hard, and how steadfastly, the soldiers fought for one another, and for the Republic.<|endoftext|>By the

  4. #4 peak

    04:30 AM⏎Capturing carbon dioxide can be done in several ways, but the most unusual approach by far is to literally feed the greenhouse gas to CO2-hungry algae.⏎Several companies have attempted

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. L8:725 strongly suppresses
  2. L8:2112 suppresses
  3. L8:2991 suppresses
  4. L7:969 excites
  5. L6:2329 excites
  6. L8:2822 excites
  7. L6:1684 suppresses
  8. L5:1327 suppresses
  9. L5:2281 weakly suppresses
  10. L4:2704 weakly excites the word 'systematic' in academic text
  11. L5:2349 weakly excites
  12. L8:2961 weakly excites
  13. L4:521 weakly suppresses
  14. L3:950 weakly excites
  15. L7:320 weakly excites
  16. L7:1186 weakly excites
  17. L6:2746 weakly excites
  18. L6:1885 weakly excites
  19. L8:1101 weakly excites
  20. L5:3010 weakly excites
  21. L6:2158 weakly suppresses
  22. L8:1350 weakly suppresses
  23. L4:1711 weakly suppresses
  24. L5:2597 weakly suppresses

Feeds later layers

  1. L12:1295 excites
  2. L20:1126 excites
  3. L16:1819 excites
  4. L20:2018 excites
  5. L12:431 excites
  6. L15:2736 excites
  7. L11:1210 excites
  8. L10:1335 excites
  9. L26:391 excites
  10. L10:1756 excites
  11. L10:991 excites
  12. L12:2773 excites
  13. L13:1424 excites
  14. L13:1792 excites
  15. L17:2481 excites
  16. L10:346 excites "each" in "each other" phrases
  17. L21:1594 weakly excites
  18. L19:2838 weakly excites
  19. L27:684 weakly excites
  20. L16:1577 weakly excites
  21. L19:2415 weakly excites
  22. L16:1374 weakly excites
  23. L12:2419 weakly excites
  24. L20:762 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.

1 values between -2.66 and -2.451 values between -1.82 and -1.612 values between -1.61 and -1.402 values between -1.19 and -0.982 values between -0.98 and -0.776 values between -0.77 and -0.5645 values between -0.56 and -0.35583 values between -0.35 and -0.142481 values between -0.14 and 0.07672 values between 0.07 and 0.2873 values between 0.28 and 0.4913 values between 0.49 and 0.707 values between 0.70 and 0.917 values between 0.91 and 1.124 values between 1.12 and 1.332 values between 1.33 and 1.544 values between 1.54 and 1.751 values between 1.75 and 1.961 values between 5.32 and 5.531 values between 5.53 and 5.74offnegativepositiveoften

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. ually
  2. edly
  3. uellement
  4. urally
  5. ingly
  6. astically
  7. ically
  8. ически
  9. mente
  10. ously

Suppresses

  1. ainting
  2. arkers
  3. aña
  4. LOGY
  5. annis
  6. berman
  7. searchData
  8. []{"
  9. curities
  10. agna