Neuron Explorer

Qwen3-0.6B

least common multiples and factors

A neuron in layer 4 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 is strongly negative on school maths pages about least common multiples (LCM) and common factors. Its positive side is weak and does not form a clear pattern. When it was turned down, the model started listing multiples and factors.

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

    .⏎Giving us a result of 250, this would be 25% of 1,000 or what is equal to the part of

  2. #2 peak

    als. The quadratic residue Gauss walk exhibits a more complex behavior whose shape is roughly determined by the remainder of modulo 24.⏎Contributed by: Erqian Wang (June

  3. #3 peak

    ) and current I(t)=Imax×sin(ωt+ΦI) where Vmax, Imax are the peak values, ω is the common angular pulsation and ΦV, ΦI are the instant phase of

  4. #4 peak

    quadrilateral. What do you notice about this quadrilateral as the⏎dynamic image changes? Can you prove your conjecture?⏎It is impossible to trisect an angle using

  5. #5 peak

    in the Photocatalytic Synthesis Group at the University of Twente. The project is part of the Advanced Research Center Chemical Building Blocks Consortium (ARC CBBC; www.arc-cbbc.nl). Within the ARC CBBC, the University of

  6. #6 peak

    a subgroup of the N numbers.⏎Another mystery was solved in researching this class. At the Brid

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: 12, 24, 36, 48, 60, 72, 9, 120, 126, 144, 16, 1

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

    multiplication.⏎Fractions - Adding Mixed Numbers⏎Learn how to Add mixed numbers with like and unlike denominators.⏎Fractions - Adding Unlike Denominators - LCM⏎Least common multiples are very useful in finding the least common denominator when adding and

  2. #2 peak

    regroup or to borrow with mixed numbers? Take a deep breath and let us take it one step at a time. Click and begin.⏎GCF and LCM by Prime Factorization⏎A straight forward way to find the greatest common factor (

  3. #3 peak

    Math - What to Expect⏎Are you considering earning your GED? Take away some of the fear of math by knowing what to expect.⏎How to Find Common Factors⏎An Efficient Method to Find Common Factors⏎How to Simplify Expressions⏎

  4. #4 peak

    9 (these are positive⏎numbers less than 1000). This will generate your test numbers. If you⏎determine that num is not divisible by 5 and 7, then increase⏎count by one.⏎Share your code

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. L3:1562 suppresses
  2. L3:703 suppresses
  3. L1:2414 suppresses
  4. L2:1657 weakly excites
  5. L3:52 weakly suppresses
  6. L2:2328 weakly suppresses
  7. L3:59 weakly excites
  8. L3:50 weakly excites
  9. L2:356 weakly excites
  10. L2:527 weakly excites
  11. L3:421 weakly suppresses
  12. L2:2468 weakly excites
  13. L2:2043 weakly excites
  14. L2:49 weakly suppresses
  15. L3:2958 weakly excites
  16. L0:2948 weakly suppresses
  17. L2:549 weakly suppresses
  18. L3:122 weakly excites
  19. L3:272 weakly excites
  20. L2:1899 weakly excites
  21. L3:1045 weakly suppresses
  22. L3:456 weakly suppresses
  23. L2:1434 weakly suppresses
  24. L3:202 weakly suppresses

Feeds later layers

  1. L18:2628 suppresses
  2. L18:1925 weakly suppresses
  3. L11:1383 weakly excites
  4. L5:1399 weakly excites
  5. L12:3001 weakly suppresses
  6. L9:679 weakly suppresses
  7. L8:1812 weakly suppresses
  8. L17:3040 weakly suppresses
  9. L24:2702 weakly suppresses
  10. L9:2555 weakly suppresses
  11. L22:978 weakly excites
  12. L15:874 weakly excites
  13. L5:211 weakly suppresses
  14. L10:2571 weakly suppresses
  15. L6:2857 weakly excites
  16. L17:1520 weakly suppresses
  17. L6:1935 weakly excites
  18. L24:598 weakly excites
  19. L7:913 weakly suppresses
  20. L6:1228 weakly excites
  21. L16:1818 weakly suppresses "two" and the link between two things
  22. L12:1907 weakly suppresses
  23. L5:860 weakly suppresses
  24. L7:1153 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 -0.96 and -0.921 values between -0.68 and -0.642 values between -0.40 and -0.363 values between -0.36 and -0.327 values between -0.32 and -0.289 values between -0.28 and -0.2413 values between -0.24 and -0.2029 values between -0.20 and -0.1677 values between -0.16 and -0.13173 values between -0.13 and -0.09317 values between -0.09 and -0.05717 values between -0.05 and -0.01950 values between -0.01 and 0.03663 values between 0.03 and 0.07403 values between 0.07 and 0.11222 values between 0.11 and 0.15143 values between 0.15 and 0.1969 values between 0.19 and 0.2343 values between 0.23 and 0.2726 values between 0.27 and 0.3118 values between 0.31 and 0.358 values between 0.35 and 0.396 values between 0.39 and 0.434 values between 0.43 and 0.472 values between 0.47 and 0.511 values between 0.51 and 0.551 values between 0.59 and 0.63offnegativepositiveoften

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. [self
  2. [state
  3. alan
  4. aupt
  5. experimental
  6. south
  7. StateManager
  8. [Any
  9. [count
  10. owards

Suppresses

  1. 辜负
  2. 瘤
  3. verständlich
  4. icast
  5. ials
  6. eg
  7. ake
  8. ег
  9. 帮助
  10. '):⏎