Neuron Explorer

Qwen3-0.6B

the word 'array'

A neuron in layer 25 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 responds to the word 'array', both in programming contexts and in ordinary uses like 'an array of problems'. Turning it up or down did not give a clear, related change in the written output.

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

    matter what you print with your first couple of builds. With that being said, congrats on your first print!⏎"Can you provide<|endoftext|>Infrasound array IS39 is located on the island of Babeldaob in the Republic

  2. #2 peak

    between nations, arraying their gods, in the popular belief, in hostility; and the only historical

  3. #3 peak

    the intricacies of pointer usage a little at a time. This approach makes it possible to present fundamental concepts using traditional high-level terminology—outputparameter, array, array subscript, string—and makes it easier

  4. #4 peak

    based on the type of problem you have, your health, and other factors. Your body is the Temple<|endoftext|>RAID, which stands short for Redundant Array of Independent Disks, is a software or hardware storage virtualization technology that permits

  5. #5 peak

    run this program, it will print the below output:⏎5 4 3 2 1⏎We need to use the range function to iterate over the array using a for loop. The range() function returns a sequence of numbers starts from

  6. #6 peak

    the first element:⏎5 4 3 2 1⏎We will use a loop to do that.⏎The values are stored in sequential order in an array and we can access these elements or values by using the index. The index starts

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: an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an an

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

    ul-Azha Day 2||Feast of Sacrifice|⏎|Saturday||September 30||Ashura||10th day of Muharram|⏎|Friday||November 03||Urs of Shah Abdul Lat

  2. #2 peak

    therapeutic human cells to diseased areas within the body using a simple magnetic effect. Their report appears in ACS' journal Langmuir.⏎Rawil Fakhrullin and colleagues explain that cell therapy aims to replace damaged or diseased cells in

  3. #3 peak

    .S.-Mexico border region. Part I introduces the case of Metales y Derivados, an abandoned, U.S.-owned maquiladora factory in Tijuana, Mexico, and the community’s struggle to compel cleanup of toxic waste at

  4. #4 peak

    the moon.⏎- Ashura: 10th Muharram*⏎Ashura is an Arabic word meaning “ten”. It is celebrated on

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. L21:1700 suppresses
  2. L23:2874 suppresses
  3. L5:357 weakly suppresses
  4. L24:2218 weakly excites
  5. L23:624 weakly excites
  6. L4:19 weakly suppresses
  7. L21:1109 weakly suppresses
  8. L8:14 weakly excites
  9. L6:7 weakly suppresses
  10. L24:594 weakly excites
  11. L6:16 weakly excites
  12. L24:382 weakly suppresses
  13. L22:989 weakly excites
  14. L9:2922 weakly suppresses
  15. L8:4 weakly excites
  16. L6:18 weakly excites
  17. L4:12 weakly suppresses
  18. L10:1946 weakly suppresses
  19. L18:1385 weakly suppresses
  20. L15:1263 weakly excites
  21. L18:2053 weakly suppresses
  22. L5:57 weakly suppresses
  23. L19:2123 weakly excites
  24. L22:681 weakly suppresses

Feeds later layers

  1. L27:1462 strongly suppresses
  2. L26:2931 suppresses
  3. L27:1857 suppresses
  4. L26:1357 weakly suppresses
  5. L27:853 weakly suppresses
  6. L27:2697 weakly excites
  7. L27:1532 weakly suppresses
  8. L26:2697 weakly excites word-start 'le' and 'log' pieces
  9. L27:2782 weakly suppresses
  10. L26:2994 weakly excites
  11. L27:1849 weakly excites
  12. L26:36 weakly suppresses
  13. L27:1493 weakly suppresses
  14. L26:2152 weakly suppresses
  15. L27:1527 weakly suppresses
  16. L26:2734 weakly excites
  17. L26:994 weakly excites
  18. L26:2963 weakly suppresses
  19. L26:1156 weakly suppresses
  20. L26:1670 weakly excites
  21. L26:2406 weakly suppresses
  22. L26:1216 weakly excites
  23. L26:384 weakly excites
  24. L26:2082 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 -7.20 and -6.551 values between -5.91 and -5.271 values between -5.27 and -4.632 values between -3.99 and -3.342 values between -3.34 and -2.703 values between -2.70 and -2.067 values between -2.06 and -1.4247 values between -1.42 and -0.78859 values between -0.78 and -0.132755 values between -0.13 and 0.51174 values between 0.51 and 1.1517 values between 1.15 and 1.798 values between 1.79 and 2.446 values between 2.44 and 3.087 values between 3.08 and 3.724 values between 3.72 and 4.362 values between 4.36 and 5.001 values between 5.00 and 5.653 values between 6.29 and 6.931 values between 6.93 and 7.573 values between 7.57 and 8.212 values between 8.21 and 8.851 values between 8.85 and 9.501 values between 17.84 and 18.48offnegativepositiveoften

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. جة
  2. Erotic
  3. 高三
  4. sterol
  5. avig
  6. ира
  7. .GetValue
  8. 初二
  9. 𝜋
  10. kos

Suppresses

  1. array
  2. array
  3. arrays
  4. Array
  5. 数组
  6. Array
  7. -array
  8. Arrays
  9. _array
  10. →array