Neuron Explorer

Qwen3-0.6B

unclear: physics constants and formulas

A neuron in layer 20 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 responds to scientific facts, such as the speed of light, heat radiation formulas and the Stefan-Boltzmann law. The pattern is loose, and turning it up did not clearly make the model write about physics.

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

    temperature)⏎and E is the flux in W/m²⏎More about this formula and background on the material properties in Planck, Stefan-Boltzmann, Kirchhoff and LTE.⏎The parameter called emissivity is the focus of

  2. #2 peak

    water is said to have a greater optical density than air.⏎Substance Speed of light (m/sec)⏎Vacuum 3 x 108⏎Air 3 x 108⏎Water 2.258 x

  3. #3 peak

    various people concerned that no one has really been interested in measuring surface emissivity properly.⏎All solid and liquid surfaces emit thermal radiation according to the Stefan-Boltzmann formula:⏎E = εσT4⏎where ε=emissivity,

  4. #4 peak

    be approximated by:⏎J = D (CWaterlooEmitter - groundwater) / membrane wall thickness⏎where D is the diffusion coefficient for the membrane material and is expressed in L2 / t.⏎Note: In gas release applications, mass is

  5. #5 peak

    of light changes and bending of light occurs.⏎In air, light travels at 3 x 108 m/sec but in water, it travels only about 2.258 x 108 m

  6. #6 peak

    Sunday, March 26, in Chase Hall Lounge, Bates College. The public is invited to attend without charge.⏎Light normally travels through a vacuum at about 186,000 miles per second. Hau and her team

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 a 4x3x3x3xxtogframe (the standard 3D version of the 4-ogtrion), and I have a trick in the right behind the 3ogtrion. I

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

    able to properly support your body; allow you to stand, walk, run, and jump; and absorb damaging shock that enters your body every time your heel hits the ground. The following are interesting facts about your feet:⏎What Causes Plantar Fasc

  2. #2 peak

    the recording below.<|endoftext|>Normal Anatomy of the Knee Joint⏎The knee is made up of four bones. The femur or thighbone is the bone connecting the hip to the knee. The tibia or shinbone connects the knee to the

  3. #3 peak

    Email to a Friend|⏎Pleural fluid analysis is a test that examines a sample of fluid that has collected in the pleural space. This is the space between the lining of the outside of the lungs (pleura) and the wall of

  4. #4 peak

    related to the number and type of joints). An extreme case with especially high degrees of freedom is given by systems in which muscles are unattached to any internal or external skeleton whatsoever. Consequently, these structures are much more flexible than jointed limbs and

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. L14:717 excites
  2. L10:876 suppresses
  3. L5:132 excites
  4. L6:2167 excites
  5. L7:87 excites
  6. L4:1421 excites
  7. L3:1048 suppresses
  8. L9:2087 suppresses
  9. L3:784 suppresses
  10. L3:388 suppresses
  11. L10:291 suppresses
  12. L9:628 suppresses
  13. L9:2792 suppresses
  14. L9:2934 weakly excites
  15. L8:1814 weakly suppresses
  16. L1:366 weakly excites
  17. L6:1254 weakly excites
  18. L9:473 weakly excites
  19. L8:2125 weakly excites
  20. L7:91 weakly excites
  21. L4:905 weakly excites
  22. L9:411 weakly suppresses
  23. L8:2846 weakly excites
  24. L10:68 weakly suppresses

Feeds later layers

  1. L23:2044 weakly excites
  2. L23:1471 weakly suppresses
  3. L24:2162 weakly suppresses
  4. L22:2932 weakly suppresses
  5. L23:1946 weakly excites
  6. L26:1412 weakly suppresses
  7. L22:2344 weakly suppresses number after 'account for' or 'over'
  8. L21:2092 weakly suppresses
  9. L22:1451 weakly suppresses
  10. L24:2487 weakly suppresses
  11. L26:1881 weakly suppresses
  12. L21:2058 weakly suppresses
  13. L23:2224 weakly suppresses
  14. L22:634 weakly excites
  15. L21:2082 weakly suppresses
  16. L24:1840 weakly suppresses
  17. L24:2291 weakly suppresses
  18. L24:1164 weakly suppresses
  19. L22:2456 weakly suppresses
  20. L23:1686 weakly suppresses
  21. L24:729 weakly excites
  22. L22:1960 weakly suppresses
  23. L21:2674 weakly suppresses
  24. L24:2676 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.

2 values between -6.95 and -6.311 values between -6.31 and -5.681 values between -5.68 and -5.044 values between -5.04 and -4.407 values between -4.40 and -3.776 values between -3.77 and -3.1324 values between -3.13 and -2.5053 values between -2.50 and -1.86102 values between -1.86 and -1.23253 values between -1.23 and -0.591803 values between -0.59 and 0.041367 values between 0.04 and 0.68144 values between 0.68 and 1.3156 values between 1.31 and 1.9522 values between 1.95 and 2.5920 values between 2.59 and 3.2215 values between 3.22 and 3.869 values between 3.86 and 4.494 values between 4.49 and 5.131 values between 5.13 and 5.765 values between 5.76 and 6.402 values between 6.40 and 7.032 values between 7.03 and 7.671 values between 7.67 and 8.301 values between 8.94 and 9.572 values between 9.57 and 10.211 values between 17.83 and 18.47offnegativepositiveoften

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. relationship
  2. relationships
  3. 关系
  4. law
  5. law
  6. 申
  7. declines
  8. 旻
  9. Law
  10. _relationship

Suppresses

  1. vergence
  2. ceği
  3. idia
  4. ertility
  5. .createUser
  6. .Unmarshal
  7. xlim
  8. ucken
  9. mutate
  10. gregator