Neuron Explorer

Qwen3-0.6B

the digit 8 in lists and numbers

A neuron in layer 18 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 fires on the digit 8, especially when it is a list number, a page or verse number, or part of a sequence. Turning it up pushed the text toward strange number-heavy and repetitive output.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens an email to the maker with the neuron already filled in).

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

    their powers of 2 do not contain zeros: 1, 2, 3, 4, 5, 6, 7, 8, 9, 13, 14, 15,

  2. #2 peak

    to fourfold greater mortality, and are up to eight times more likely to die within the first 24 hours following injury [2-4,7,8].⏎Injury to brain tissue may predispose to acute traumatic coagulopathy

  3. #3 peak

    pneumonia (nosocomial pneumonia)⏎06 - Measures to prevent surgical site infections⏎07 - Color coding of cleaning materials and equipment to prevent infections⏎08 - Measures to control performance of correct procedure at the correct body site⏎09

  4. #4 peak

    the uses of it to business?⏎problem 6: Describe the components of MIS.⏎problem 7: Differentiate between desktop PC and portable PC.⏎problem 8: Define the term enterprise application software. describe common types of it.⏎problem

  5. #5 peak

    x depth x height);⏎3. Temperature range⏎4. Temperature display accuracy⏎5. Temperature stability⏎6. Temperature uniformity⏎7. Heating time⏎8. Internal material⏎SUS304 stainless steel plate, thickness 1

  6. #6 peak

    .⏎What Causes Cold Sore?⏎The most common cold sore causes is a virus known as Herpes simplex virus type 1 or HSV-1. About 80 percent of people will get the virus before they reach the age of 1

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 was a child in a small town, and I was a boy. I was born with a color that was like a spark, that I could see, and that I could see it with my heart. I could see the truth,

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’s available in print. This makes finding early examples of colloquial language very difficult, as most non-standard English doesn’t make it into publication. Aight was probably spoken aloud before the 90s, but if nobody recorded it

  2. #2 peak

    3 and 1994, respectively. Upon first glance, this seems far too late to me. Surely there were rappers rhyming with aight in the 1980s. Why doesn’t the OED cite

  3. #3 peak

    Italians say: Gluttony kills more than the sword. NB).⏎The company also found

  4. #4 peak

    ”. The song wasn’t what you’d call a smash hit, but I mention it today because the editors of the OED have just put its namesake aight into

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. L4:847 suppresses
  2. L16:55 suppresses
  3. L17:253 excites
  4. L16:113 suppresses
  5. L16:142 excites
  6. L0:2272 excites
  7. L17:350 suppresses
  8. L10:233 suppresses
  9. L5:204 excites
  10. L16:374 excites
  11. L17:241 excites
  12. L17:710 excites
  13. L2:1866 excites
  14. L17:420 excites
  15. L15:89 excites
  16. L17:765 suppresses
  17. L5:890 suppresses
  18. L16:215 suppresses
  19. L2:1611 suppresses
  20. L16:461 excites
  21. L16:673 excites
  22. L16:260 excites
  23. L15:114 excites
  24. L17:378 suppresses

Feeds later layers

  1. L20:1630 strongly excites
  2. L20:121 excites
  3. L20:147 suppresses
  4. L19:683 suppresses
  5. L26:1602 suppresses
  6. L21:979 suppresses
  7. L25:2442 suppresses
  8. L26:2635 suppresses
  9. L19:2501 suppresses
  10. L19:2017 suppresses
  11. L19:2905 suppresses
  12. L26:1341 suppresses
  13. L19:754 suppresses
  14. L20:1486 suppresses
  15. L22:2379 suppresses
  16. L20:287 excites
  17. L19:2787 suppresses
  18. L26:1054 suppresses
  19. L19:311 suppresses
  20. L20:2017 suppresses
  21. L20:1852 suppresses
  22. L26:1883 excites
  23. L20:950 suppresses
  24. L19:715 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.

42 values between -2.62 and -1.67208 values between -1.67 and -0.723641 values between -0.72 and 0.2310 values between 0.23 and 1.171 values between 2.12 and 3.071 values between 3.07 and 4.021 values between 13.49 and 14.442 values between 24.86 and 25.811 values between 25.81 and 26.751 values between 34.33 and 35.28offnegativepositiveoften

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. eenth
  2. (proxy
  3. Braves
  4. ⏎ ⏎
  5. reeze
  6. ⏎ ⏎ ⏎
  7. Angelo
  8. indexPath
  9. puff
  10. OpenHelper

Suppresses

  1. ucha
  2. idity
  3. ince
  4. eline
  5. ariant
  6. tor
  7. Lex
  8. aton
  9. MEM
  10. HEN