Neuron Explorer

Qwen3-0.6B

'to' after adapt/adjust verbs

A neuron in layer 10 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 'to' right after verbs like 'adapt', 'adjust' or 'adapted', as in 'adapt to climate change'. When it was turned up, the model's text drifted toward talk of change and adjustment, but the link to the prompts was loose.

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

    a Russian scientist, N.V. Lazarev, who was interested in substances that helped the body adapt to physical and emotional stress. Lazarev thought that adaptogens should:⏎- Produce

  2. #2 peak

    their daughter have spent most of 2008 living in primitive facilities near the shores of Lake Tanganyika.⏎There, the family has learned to adjust to life in

  3. #3 peak

    whose sweep around the sun at that time was a scientific bonus. Daily medical experiments took the most time, as the spacemen gathered data on how their bodies adapted to their weightless environment. The astronauts took four two- man space walks, with

  4. #4 peak

    people. The video highlights the need for accurate, continuous, and accessible data and computer models from NASA satellites to track and predict the challenges farmers face as they adjust to a changing climate.⏎This video is the first of a three-video series from the

  5. #5 peak

    to Solomon Islands⏎In Solomon Islands and across the Pacific Islands region, the U.S. Agency for International Development (USAID) supports programs that help communities adapt to the negative impacts of global climate change and supports disaster relief efforts and disaster risk reduction

  6. #6 peak

    morphogens. And even cancer cells can use morphogens to grow, induce a blood supply, and metastasize.⏎Although the concept of cell organization in response to these morphogen gradients is well documented, little is known about how these subtle concentration

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 can't have me and me, I can't have you and me. So I'm thinking, I'm thinking. Then, I can't think, I can't think. This is the problem. I mean, I'm thinking

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

    electrodes or plates, an electrolyte that permits ionic conduction, one or more negative electrodes or plates, separators between plates of opposite polarity, and a container for all the above.⏎Battery Life — The period during which

  2. #2 peak

    Munich,⏎will also return this year.⏎Computer simulations suggest that⏎a Morning Glory is caused by the collision of two sea breezes over Cape⏎York the preceding evening. "We want to nail down the

  3. #3 peak

    charged electrons. While the positively charged ions pass through the fuel cell, the negatively charged electrons are diverted and directed through a wire to create an electric current. The electrons complete the detour to meet up with the ions in the final segment of the

  4. #4 peak

    others that need a bit more use of a microscope such as extinction (the angle at which a mineral goes black and you rotate the slide) and birefringence (the colour of the mineral using crossed polars).⏎Minerals have different

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. L7:1782 weakly suppresses
  2. L7:2364 weakly suppresses
  3. L8:2797 weakly suppresses
  4. L6:1490 weakly suppresses
  5. L8:181 weakly suppresses
  6. L9:2506 weakly excites
  7. L7:2957 weakly excites
  8. L6:2173 weakly suppresses
  9. L5:1224 weakly excites
  10. L6:1158 weakly excites
  11. L6:2756 weakly suppresses
  12. L9:2757 weakly excites
  13. L8:706 weakly suppresses
  14. L3:429 weakly suppresses
  15. L9:2643 weakly suppresses
  16. L8:137 weakly excites
  17. L4:1431 weakly excites
  18. L7:564 weakly suppresses
  19. L6:615 weakly excites
  20. L4:1013 weakly suppresses
  21. L8:1469 weakly suppresses
  22. L7:3040 weakly excites
  23. L9:2404 weakly suppresses
  24. L1:2922 weakly excites

Feeds later layers

  1. L19:2102 excites
  2. L16:2556 excites
  3. L17:270 weakly suppresses
  4. L11:1350 weakly suppresses
  5. L22:755 weakly excites 'all' or 'any' in 'people of all ages'
  6. L27:1231 weakly excites
  7. L20:2028 weakly excites
  8. L14:640 weakly excites
  9. L17:2165 weakly excites
  10. L24:2320 weakly excites
  11. L12:2994 weakly excites
  12. L14:2333 weakly excites
  13. L14:556 weakly excites
  14. L14:694 weakly suppresses
  15. L16:2163 weakly excites
  16. L14:2658 weakly suppresses
  17. L23:977 weakly suppresses
  18. L15:1270 weakly excites
  19. L12:1137 weakly excites
  20. L12:1465 weakly excites
  21. L12:2410 weakly excites
  22. L21:1633 weakly suppresses
  23. L17:1195 weakly excites
  24. L14:539 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 -1.65 and -1.531 values between -1.53 and -1.421 values between -1.42 and -1.314 values between -1.31 and -1.202 values between -1.20 and -1.096 values between -1.09 and -0.984 values between -0.98 and -0.8714 values between -0.87 and -0.7615 values between -0.76 and -0.6521 values between -0.65 and -0.5435 values between -0.54 and -0.4261 values between -0.42 and -0.31160 values between -0.31 and -0.20411 values between -0.20 and -0.091676 values between -0.09 and 0.021001 values between 0.02 and 0.13286 values between 0.13 and 0.24100 values between 0.24 and 0.3531 values between 0.35 and 0.4724 values between 0.47 and 0.5817 values between 0.58 and 0.6911 values between 0.69 and 0.804 values between 0.80 and 0.913 values between 0.91 and 1.023 values between 1.02 and 1.132 values between 1.13 and 1.241 values between 1.24 and 1.352 values between 1.35 and 1.464 values between 1.46 and 1.582 values between 1.69 and 1.802 values between 1.80 and 1.912 values between 2.02 and 2.131 values between 2.69 and 2.80offnegativepositiveoften

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. 处境
  2. 传播
  3. 阴
  4. 难度
  5. esp
  6. 生存
  7. 气候
  8. exposures
  9. 现实生活
  10. ég

Suppresses

  1. 最快的
  2. ittal
  3. ware
  4. mach
  5. uffed
  6. ITES
  7. 最多的
  8. responsable
  9. terminate
  10. .DataTable