Neuron Explorer

Qwen3-0.6B

the number 1 as a unit value

A neuron in layer 10 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 number 1 when it means a standard or normalized amount, like a speed of 1, a cosine of 1, or a value set to unity. It seems to pick up on 'one unit' meanings more than on the digit itself. Turning it up did not produce any clear theme in the written text.

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

    2pi). a) Using its own inner impulse (h) circle - particle moves ( as a wheel) in a straight line with constant speed c = 1. We call such particle - ?photon?.

  2. #2 peak

    constraint and characterize the solution to her intertemporal maximization problem.⏎c) Consider the full competitive market equilibrium in this economy; normalize the constant labor force to unity such that kt=Kt at all t. Characterize the equilibrium dynamics of

  3. #3 peak

    x = L/ 6?⏎Answer to relevant QuestionsWhich has the lowest (ground-state) energy, an electron trapped in a one dimensional box of length 10-6 m or one with length 10-10 m?

  4. #4 peak

    an HTML image tag. It displays a 1×1 transparent image then proceeds to execute PHP scripts based on the pseudocron schedule file

  5. #5 peak

    a given color that differs slightly from a primary color; "after several trials he mixed the shade of pink that she wanted"⏎t

  6. #6 peak

    (gas or liquid) from a zone of lower external concentration of same species in the groundwater. In mathematical terms, the net amount of material diffusing across a unit cross-section (J, flux) perpendicular to a membrane of known thickness (x

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 don't think that...". "The following is a list of people...": "This is a list of people..." "This is a list of people": "Message:" "Messages": "This is a list of people

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

    services and evaluate video quality in six categories of digital defects on a scale of one to five (one being unwatchable and five being spectacular).”⏎“In addition

  2. #2 peak

    It typically features a touch plate known as "Sonic Strings", preset rhythms, auto-bass line functionality, and buttons for major, minor, and 7th chords. The most basic method of playing the instrument is to press the chord buttons

  3. #3 peak

    acid or something like that, the association will be greatly weakened or eliminated.⏎Some biological structures (for example, "promoters") are not as sensitive to base pair sequences as proteins are to amino acid sequences, but these are exceptional; we are

  4. #4 peak

    use this pattern so often that we have created a name and a symbol for it. 8×7×6×5×4×3×2×1 is written as 8! and we call it "eight factorial." You probably

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. L8:184 suppresses
  2. L9:1373 suppresses
  3. L6:902 excites
  4. L9:1348 weakly suppresses
  5. L4:1100 weakly excites
  6. L5:513 weakly suppresses
  7. L7:1524 weakly suppresses
  8. L8:879 weakly excites
  9. L3:244 weakly suppresses
  10. L7:1499 weakly excites
  11. L9:1989 weakly excites
  12. L9:1691 weakly suppresses
  13. L9:2915 weakly suppresses
  14. L7:2156 weakly excites
  15. L5:303 weakly excites
  16. L9:1169 weakly suppresses
  17. L8:2742 weakly suppresses
  18. L8:1701 weakly suppresses
  19. L4:2090 weakly excites
  20. L7:1986 weakly excites
  21. L9:673 weakly suppresses
  22. L0:969 weakly excites
  23. L8:318 weakly excites
  24. L7:1947 weakly excites

Feeds later layers

  1. L11:871 suppresses zero and infinity as values
  2. L11:1852 excites the digit 1 in numbers
  3. L11:2291 excites numbers inside citation references
  4. L11:836 excites
  5. L17:1615 weakly suppresses
  6. L13:1479 weakly excites
  7. L18:2732 weakly suppresses
  8. L23:2219 weakly suppresses
  9. L12:2434 weakly excites
  10. L16:1012 weakly excites 'one' before 'of' in 'is one of the'
  11. L17:1154 weakly excites
  12. L20:547 weakly suppresses
  13. L16:1564 weakly suppresses
  14. L12:303 weakly suppresses
  15. L11:1509 weakly excites
  16. L16:2624 weakly excites
  17. L26:1882 weakly excites
  18. L20:2976 weakly suppresses
  19. L16:536 weakly suppresses
  20. L22:1639 weakly suppresses
  21. L13:1106 weakly excites
  22. L11:694 weakly suppresses
  23. L12:894 weakly excites
  24. L25:2345 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 -1.35 and -1.301 values between -1.06 and -1.001 values between -0.70 and -0.651 values between -0.65 and -0.591 values between -0.59 and -0.537 values between -0.53 and -0.478 values between -0.47 and -0.4112 values between -0.41 and -0.3538 values between -0.35 and -0.2971 values between -0.29 and -0.23140 values between -0.23 and -0.17271 values between -0.17 and -0.11550 values between -0.11 and -0.051005 values between -0.05 and 0.01837 values between 0.01 and 0.07447 values between 0.07 and 0.12258 values between 0.12 and 0.18147 values between 0.18 and 0.2460 values between 0.24 and 0.3030 values between 0.30 and 0.3612 values between 0.36 and 0.422 values between 0.42 and 0.485 values between 0.48 and 0.541 values between 0.54 and 0.601 values between 0.66 and 0.721 values between 0.95 and 1.01offnegativepositiveoften

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. lox
  2. ştur
  3. Apprent
  4. Magical
  5. =BitConverter
  6. sağlam
  7. wij
  8. _AHB
  9. itarian
  10. urre

Suppresses

  1. holes
  2. handles
  3. asl
  4. segments
  5. OM
  6. segment
  7. essel
  8. SE
  9. ses
  10. rs