Neuron Explorer

Qwen3-0.6B

unclear: mixed, mostly technical prose

A neuron in layer 14 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 a grab bag of positions in technical text, such as a blank before a digit, 'physically', 'costs' or 'energy'. No single theme stands out. Turning it up produced unrelated text.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    What is the centripetal acceleration of the same sphere if both distance R and speed s are doubled?⏎B) a / 4⏎C) a / 2⏎D) 2 a⏎E) 4 a⏎What is

  2. #2 peak

    obtain any kind of textual and visual information from the ever-growing online knowledge base through our computer or smart phone. For instance, when reading articles you get their corresponding text file executed, while when viewing images you have their image files displayed.

  3. #3 peak

    of products—agents that occlude dentin tubules and desensitizing agents that interfere with the transmission of nerve impulses.⏎Occluding agents act by physically covering or “plugging” the open, exposed dentin tubules, thus

  4. #4 peak

    small radiators in the functional spaces.⏎In a Passivhaus project, the value saved by avoiding a large central heating and distribution system, and its ongoing fuel costs, is invested instead in triple glazing (and sometimes, on north sides,

  5. #5 peak

    in your home, and watch the savings add up. Some people also prefer light emitting diodes (LEDs), which can be more expensive but use very little energy.⏎4. Energy-Conserving Building Envelope⏎Most houses leak air.

  6. #6 peak

    the VAT as well as the currency.⏎The task: Depending on the country and the data type you want to get the correct value from the table. For example, you select “Canada” and “VAT”, you want to get 5

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 following results in the case of a case of the case of the case of the case of the case of the case of the case of the case of the case of the case of the case of the case of the case of the case

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

    measured.⏎Millimeter (abbreviated mm) – this is one thousandth of a meter. In scientific notation, 1 millimeter is 1 – E3 m, which means 0.001 x 1

  2. #2 peak

    A single heat pulse will switch the magnetic orientation of a nanometer-sized magnetic grain in just a few picoseconds (1 picosecond is 0.000000000

  3. #3 peak

    FLs). Installing one CFL saves $15 annually, according to the Rocky Mountain Institute, a nonprofit energy research group. Multiply that by the number of lamps and fixtures in your home, and watch the savings add up. Some people also prefer

  4. #4 peak

    has three parts, Part A, short answer, has 1 problem (12 points). Part B has 5 shorter problems (7 points each, so 35 points). Part C has 3 traditional problems (15 points each

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. L13:2712 suppresses
  2. L13:868 suppresses
  3. L13:2805 excites
  4. L13:1339 suppresses
  5. L13:2470 suppresses
  6. L13:2140 excites
  7. L12:2817 excites
  8. L12:2942 suppresses
  9. L13:1667 excites
  10. L10:2193 excites
  11. L12:2436 excites
  12. L9:1555 suppresses
  13. L3:661 suppresses
  14. L13:1774 suppresses
  15. L13:1059 suppresses
  16. L13:2724 suppresses
  17. L12:1935 excites
  18. L12:2137 excites
  19. L13:864 suppresses
  20. L11:1894 weakly excites
  21. L13:2987 weakly suppresses
  22. L13:994 weakly excites
  23. L12:1375 weakly suppresses
  24. L13:2413 weakly excites

Feeds later layers

  1. L15:3026 suppresses
  2. L15:1481 suppresses
  3. L15:2487 suppresses
  4. L15:874 excites
  5. L18:1948 suppresses
  6. L16:858 excites
  7. L18:1446 excites
  8. L16:2337 suppresses
  9. L15:1445 suppresses
  10. L17:204 suppresses
  11. L15:922 suppresses
  12. L15:475 weakly excites
  13. L16:1265 weakly excites
  14. L19:2149 weakly suppresses
  15. L21:1216 weakly suppresses
  16. L15:427 weakly excites
  17. L16:422 weakly excites
  18. L18:435 weakly excites
  19. L16:2425 weakly excites
  20. L16:348 weakly excites
  21. L17:2179 weakly suppresses
  22. L15:2604 weakly excites
  23. L15:1346 weakly excites
  24. L15:2610 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 -2.03 and -1.961 values between -0.79 and -0.722 values between -0.72 and -0.654 values between -0.65 and -0.585 values between -0.58 and -0.501 values between -0.50 and -0.438 values between -0.43 and -0.3626 values between -0.36 and -0.2941 values between -0.29 and -0.21111 values between -0.21 and -0.14288 values between -0.14 and -0.071156 values between -0.07 and 0.011179 values between 0.01 and 0.08584 values between 0.08 and 0.15308 values between 0.15 and 0.22123 values between 0.22 and 0.3046 values between 0.30 and 0.3716 values between 0.37 and 0.441 values between 0.44 and 0.522 values between 0.52 and 0.591 values between 0.59 and 0.664 values between 0.81 and 0.88offnegativepositiveoften

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. [name
  2. 毋
  3. يد
  4. [source
  5. .Atoi
  6. berries
  7. خام
  8. ataires
  9. 白白
  10. 钮

Suppresses

  1. hä
  2. afka
  3. PRS
  4. lescope
  5. erview
  6. lingen
  7. ezier
  8. 动机
  9. 金字塔
  10. 最小