Neuron Explorer

Qwen3-0.6B

"of" after the word "number"

A neuron in layer 12 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron lights up on the word "of" when it follows "number", as in "the number of" or "the number of counts". When it was turned up, the model's writing drifted toward counting and numbers, though the link 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

    , 2, and 1.8° per step.⏎Step angle = 360°/No of steps per revolution⏎Where m = Number of Phase winding on the

  2. #2 peak

    less prone to interference in comparison to RF technology.⏎DPI and FPS⏎DPI (dots per inch) and FPS (frames per second) are the number of counts in an inch of movement and the number of times the sensor reads the surface

  3. #3 peak

    this outbreak, I had occasion to review some clippings from<|endoftext|>A. Physical Characteristics⏎- How many feathers are on a turkey? An adult turkey has 5,000-6,000 feathers on its body,

  4. #4 peak

    the number of teeth on the Screw itself. A larger number of starts results in a more robust mechanism with a greater ability to transmit torque, but multiple ‘starts’ can sometimes be incompatible with a small ‘lead’ due to space limitations.⏎Lead

  5. #5 peak

    can now code this algorithm using Python to reveal the answer to the initial question: how many lego bricks are needed to build planet Earth!⏎Number of lego bricks⏎If you have completed this algorithm, the final answer should be approximatively

  6. #6 peak

    children per woman. This rate, which indicates the average number of children that women would have during their lifetime if they conformed to the current age-specific fertility

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 have been thinking about how many I have been thinking about... Let's see, it's a function of... Let's say 2 to 3, which means 2 to 3, 2 to 3,

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

    what your right hand possesses. That is more likely that you will not be unjust.'⏎This verse has been interpreted to mean that Muslim men are allowed to marry up to four wives, but if they fear that they will not be able to treat them

  2. #2 peak

    Ask him to multiply the coin in the left hand by 17 and to say 'OK' when he has the answer. If it took about the same amount of time for each, then the nickel is in the right hand since 1

  3. #3 peak

    ? after the 24th attempt?⏎Let’s assume that we have a more general problem. There are n questions, and a(n) is the smallest number of times we need to take the test to guarantee that we can figure out the

  4. #4 peak

    . This radium emits tiny amounts of radon into the atmosphere. On average, one part of radon is present in 1 x 1021 part of air.Radon is also present in some spring waters, including Hot

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. L9:628 excites
  2. L11:1889 suppresses
  3. L10:2300 suppresses
  4. L9:1197 excites
  5. L10:978 suppresses
  6. L9:2690 suppresses
  7. L8:1029 suppresses
  8. L11:52 excites
  9. L10:68 excites
  10. L11:1455 suppresses
  11. L11:2003 suppresses
  12. L6:1849 excites
  13. L10:1954 excites
  14. L11:2818 excites
  15. L8:1939 suppresses
  16. L10:2531 excites
  17. L10:266 suppresses
  18. L10:1539 excites
  19. L9:1087 suppresses
  20. L11:979 suppresses
  21. L6:1767 suppresses
  22. L10:2791 excites
  23. L10:1618 suppresses
  24. L10:2063 suppresses

Feeds later layers

  1. L17:1727 strongly suppresses
  2. L20:1113 suppresses
  3. L17:1581 excites
  4. L17:1912 suppresses
  5. L19:1033 suppresses
  6. L22:784 suppresses
  7. L20:1528 suppresses blank spot before a number
  8. L16:2448 suppresses
  9. L20:1404 suppresses
  10. L20:595 suppresses
  11. L15:1535 excites
  12. L15:1521 suppresses
  13. L18:2694 suppresses
  14. L17:2711 suppresses
  15. L15:856 excites
  16. L16:2637 suppresses
  17. L21:756 suppresses
  18. L23:1404 suppresses
  19. L13:1629 suppresses
  20. L13:1564 excites
  21. L20:509 excites
  22. L17:2038 suppresses
  23. L14:2832 suppresses
  24. L17:1271 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 -1.69 and -1.591 values between -1.49 and -1.381 values between -1.38 and -1.282 values between -1.28 and -1.183 values between -1.18 and -1.081 values between -1.08 and -0.982 values between -0.98 and -0.874 values between -0.87 and -0.773 values between -0.77 and -0.679 values between -0.67 and -0.577 values between -0.57 and -0.4716 values between -0.47 and -0.3749 values between -0.37 and -0.26237 values between -0.26 and -0.16737 values between -0.16 and -0.061911 values between -0.06 and 0.04629 values between 0.04 and 0.14175 values between 0.14 and 0.2573 values between 0.25 and 0.3522 values between 0.35 and 0.459 values between 0.45 and 0.554 values between 0.55 and 0.654 values between 0.65 and 0.752 values between 0.75 and 0.861 values between 0.86 and 0.963 values between 0.96 and 1.061 values between 1.57 and 1.671 values between 2.28 and 2.38offnegativepositiveoften

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. orque
  2. 材
  3. incent
  4. damp
  5. 墙壁
  6. 墙体
  7. Specs
  8. 比率
  9. walls
  10. yếu

Suppresses

  1. count
  2. ROWS
  3. ifferent
  4. etti
  5. .index
  6. illy
  7. count
  8. zähl
  9. idx
  10. _indices