Neuron Explorer

Qwen3-0.6B

unclear: weak, scattered activations

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 barely responds to anything. Its strongest examples are weak and come from very different texts, so there is no clear pattern to describe. Turning it up gave mostly repetitive text.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    the Abyssins have not many images, they have great numbers of pictures, and perhaps pay them somewhat too high a degree of worship. The severity of their fasts is equal to that of the primitive church. In Lent they never eat till after

  2. #2 peak

    learner<|endoftext|>n.交響樂 [an elaborate instrumental composition in three or more movements, similar in form to a sonata but written for an orchestra (管弦樂隊) and usually of far grander proportions and more varied elements.]⏎

  3. #3 peak

    (formerly referred to as the reciprocal ohm or mho). Oliver Heaviside coined the term in September 1885.⏎Relation to other quantitiesEdit⏎As mentioned, conductance is related to resistance by:⏎for purely resistive

  4. #4 peak

    Journal suggests that it might be possible.⏎That's because a team of Swiss researchers found that when a hormone in the brain, erythropoietin (Epo), was elevated in mice, they were more motivated to exercise. In addition,

  5. #5 peak

    .What is the difference between MOV and MVI?⏎12. What are the functions of RIM, SIM, IN?⏎13. What is the immediate addressing mode?⏎14.

  6. #6 peak

    .<|endoftext|>Hamlet Essay, Research Paper⏎Hamlet is based on a young prince of Denmark that must uncover the truth about his fathers death. Hamlet a play that tells the story of a young prince who’s father recently died. Hamlets

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 am a number!" - and I will use the number to calculate the future value of the number. Now that is what? Let me know it. I have to calculate the future value of the number, but I am not.

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

    are carried over to the new data directory.⏎Stop the existing MySQL instance using the data directory. This must be a clean shutdown<|endoftext|>On April 16, 1853, the first train left Bombay for Thana. The

  2. #2 peak

    wrote in her diary, describing the tethered balloon being pulled along the National Mall. “He seemed to be enjoying his ride greatly.”⏎With this attention-grabbing stunt, Lowe was determined to

  3. #3 peak

    esite stratovolcano in the Islands of Four Mountains, a volcanic group in the Aleutian Arc. Like all stratovolcanoes, Mount Cleveland grew as explosive eru

  4. #4 peak

    really allowed to ask: “How many Americans have died after taking the COVID vaccine?”1⏎If you haven’t paid attention, the answer to this verboten (forbidden) question may shock you. Carlson points out (inaccurately

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. L3:218 excites
  2. L3:604 suppresses
  3. L3:122 excites
  4. L3:464 excites
  5. L3:115 suppresses
  6. L3:188 excites
  7. L0:1301 suppresses
  8. L0:1224 suppresses
  9. L2:75 suppresses
  10. L2:111 suppresses
  11. L2:49 suppresses
  12. L3:59 excites
  13. L0:178 suppresses
  14. L2:1710 suppresses
  15. L3:456 suppresses
  16. L3:480 excites
  17. L3:1616 excites
  18. L3:2369 suppresses
  19. L3:294 excites
  20. L3:2543 excites
  21. L2:70 excites
  22. L3:50 excites
  23. L2:154 suppresses
  24. L3:421 suppresses

Feeds later layers

  1. L5:14 excites
  2. L5:230 suppresses
  3. L5:72 suppresses
  4. L5:2860 excites
  5. L5:81 excites
  6. L7:46 excites
  7. L15:1208 excites
  8. L6:49 excites
  9. L6:19 weakly suppresses second half of proper names
  10. L9:2567 weakly excites
  11. L5:69 weakly excites
  12. L16:194 weakly suppresses
  13. L5:414 weakly excites
  14. L16:454 weakly suppresses
  15. L15:402 weakly excites
  16. L5:129 weakly suppresses
  17. L6:2 weakly excites
  18. L9:3 weakly suppresses
  19. L14:270 weakly excites
  20. L14:2784 weakly suppresses
  21. L16:97 weakly suppresses
  22. L5:1052 weakly excites
  23. L12:994 weakly excites
  24. L6:413 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 -1.12 and -1.071 values between -1.02 and -0.961 values between -0.91 and -0.863 values between -0.86 and -0.814 values between -0.76 and -0.714 values between -0.71 and -0.669 values between -0.66 and -0.6119 values between -0.61 and -0.5634 values between -0.56 and -0.5136 values between -0.51 and -0.4681 values between -0.46 and -0.4199 values between -0.41 and -0.36140 values between -0.36 and -0.30158 values between -0.30 and -0.25252 values between -0.25 and -0.20261 values between -0.20 and -0.15292 values between -0.15 and -0.10323 values between -0.10 and -0.05368 values between -0.05 and -0.00330 values between -0.00 and 0.05317 values between 0.05 and 0.10278 values between 0.10 and 0.15258 values between 0.15 and 0.20195 values between 0.20 and 0.25127 values between 0.25 and 0.3097 values between 0.30 and 0.3679 values between 0.36 and 0.4159 values between 0.41 and 0.4625 values between 0.46 and 0.5122 values between 0.51 and 0.5615 values between 0.56 and 0.6111 values between 0.61 and 0.664 values between 0.66 and 0.713 values between 0.71 and 0.761 values between 0.76 and 0.811 values between 0.86 and 0.91offnegativepositiveoften

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. ny
  2. iy
  3. att
  4. alm
  5. 看起来
  6. ell
  7. oki
  8. sy
  9. SCORE
  10. ine

Suppresses

  1. .shtml
  2. ��
  3. erculosis
  4. icles
  5. writers
  6. aments
  7. urers
  8. itors
  9. wizards
  10. icians