Neuron Explorer

Qwen3-0.6B

technical terms mid-phrase, mostly engineering

A neuron in layer 9 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 pieces of technical terms in engineering, chemistry and biology writing, such as 'Mill' in 'End Milling', 'Weld' in 'Welding', or 'me' in a gene modification code. It goes slightly negative on the middle of words like 'servos' and 'with' after 'interact'. Turning it up or down did not give a clear, shared output theme.

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

    Angle in End Milling⏎End mills are used to form shapes and holes during milling and can cut

  2. #2 peak

    , processes that regulate gene expression. They found about 80 percent of pediatric hindbrain ependymomas had substantially reduced levels of H3K27me3, a critical histone H3 protein modification. These tumor samples consistently tied

  3. #3 peak

    units, type ‘UN’ into your keyboard and then select the ‘ENTER’ key. A dialog box should pop-up on the screen allowing you to specify the unit

  4. #4 peak

    point (2, 4)?⏎November 18, 2010⏎biology / plasmolysis of human red blood cells⏎Plasmolysis of human red blood cells would occur if the cell were in .. solution A

  5. #5 peak

    basic knowledge about rake angle and introduces the latest technology used to take accurate rake angle measurements.⏎- Rake Angle⏎- Positive and Negative Rake Angle in End Milling⏎- Relationship Between Cutting Tool Angle, Rake Angle, and Relief Angle

  6. #6 peak

    transfer commonly used on low alloy steels. This all position wire normally used in appliions which will produce a⏎Penetration Form of DC-TIG Arc Welding Using Flux

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 like the color blue, the color green, and the color yellow." What does that mean? Answer: [Insert image] The answer is to use the image or a link. Answer: [Insert image] The answer is

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

    a wide variety of things - it doesn't have an Operating System (OS) per se. Arduino has a great deal of support for accessing the board and driving servos, etc., but it is limited and doesn't provide what an OS provides

  2. #2 peak

    ASPBERRY Pi and ARDUINO COMPUTERS⏎The Arduino is a wonderful platform for handling the lower level work of a robot - reading sensors, driving servos, and blinking lights. There is a fair amount of RAM on board, and

  3. #3 peak

    is a solution.⏎The program svn, which is used on the command line interact with the SVN server, has a diff function too: svn diff.⏎You can run

  4. #4 peak

    'S', then click at the end of the word and type<|endoftext|>Mallorca’s popular tourist railway

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. L4:2279 excites
  2. L6:989 excites
  3. L8:676 suppresses
  4. L8:12 excites
  5. L8:1005 suppresses
  6. L7:2730 excites
  7. L6:18 excites
  8. L6:1206 weakly suppresses
  9. L7:2764 weakly excites
  10. L8:7 weakly excites
  11. L7:1980 weakly suppresses
  12. L8:4 weakly excites
  13. L0:2376 weakly suppresses
  14. L6:1795 weakly suppresses
  15. L6:438 weakly suppresses
  16. L8:1542 weakly excites
  17. L7:2915 weakly excites
  18. L7:1212 weakly excites
  19. L6:827 weakly suppresses
  20. L0:1057 weakly suppresses
  21. L6:2881 weakly suppresses
  22. L8:13 weakly suppresses
  23. L3:439 weakly excites
  24. L6:7 weakly suppresses

Feeds later layers

  1. L10:1675 suppresses
  2. L21:2025 suppresses
  3. L10:2446 suppresses
  4. L10:2806 excites
  5. L13:2456 excites
  6. L10:2777 suppresses
  7. L21:3021 suppresses
  8. L10:1629 excites
  9. L10:2544 excites
  10. L11:96 weakly excites
  11. L17:1534 weakly suppresses
  12. L11:976 weakly excites
  13. L17:2028 weakly excites
  14. L11:1029 weakly suppresses
  15. L20:953 weakly suppresses
  16. L12:1223 weakly excites
  17. L14:2775 weakly suppresses
  18. L14:2447 weakly excites
  19. L18:2943 weakly suppresses
  20. L16:2589 weakly excites
  21. L11:2037 weakly excites
  22. L20:1628 weakly excites
  23. L10:1996 weakly suppresses
  24. L25:1764 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 -0.67 and -0.641 values between -0.64 and -0.611 values between -0.42 and -0.391 values between -0.36 and -0.327 values between -0.32 and -0.293 values between -0.29 and -0.2612 values between -0.26 and -0.2328 values between -0.23 and -0.2030 values between -0.20 and -0.1767 values between -0.17 and -0.1383 values between -0.13 and -0.10150 values between -0.10 and -0.07310 values between -0.07 and -0.04629 values between -0.04 and -0.01897 values between -0.01 and 0.02582 values between 0.02 and 0.06352 values between 0.06 and 0.09254 values between 0.09 and 0.12163 values between 0.12 and 0.15112 values between 0.15 and 0.1870 values between 0.18 and 0.2141 values between 0.21 and 0.2538 values between 0.25 and 0.2830 values between 0.28 and 0.3116 values between 0.31 and 0.349 values between 0.34 and 0.374 values between 0.37 and 0.415 values between 0.41 and 0.444 values between 0.44 and 0.472 values between 0.47 and 0.501 values between 0.50 and 0.533 values between 0.53 and 0.562 values between 0.56 and 0.60offnegativepositiveoften

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. arium
  2. 了自己的
  3. elian
  4. 储备
  5. childhood
  6. 保税
  7. lesia
  8. amphetamine
  9. październ
  10. spreading

Suppresses

  1. tempts
  2. rome
  3. testers
  4. カメ
  5. беж
  6. locate
  7. APTER
  8. ATER
  9. tester
  10. ients