Neuron Explorer

Qwen3-0.6B

the digit 1 starting years

A neuron in layer 24 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 lights up on the digit 1 when it starts a year in the 1700s or 1800s, such as the 1 in 1815 or 1766. Turning it up made the model's writing wander into odd, unrelated topics like social media and the weather, so the steering result doesn't clearly reflect the trigger.

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

    ing boats which were managed by watermen. These boats were known as Wherries or water taxis as we would call them.⏎Steam boats were introduced in 1815 and by 1850 were carrying more than a million

  2. #2 peak

    Spanish Empire and the rise of America as a major world power with several new possessions.⏎Britain Repeals the Stamp Act⏎On March 18, 1766, British Parliament repealed the Stamp Act. Passed a year earlier,

  3. #3 peak

    catcher mounted on the back of Daniel Webster.⏎The print might have been produced in Boston, a center of bitter opposition to the Fugitive Slave Act in 1850 and 1851.⏎Please post your comment below to

  4. #4 peak

    limits a just and liberal policy, and to give that humane and considerate attention to their rights and their wants,” Jackson declared in his first inaugural address in 1829

  5. #5 peak

    and how she came up with the idea, and the sequence of events?”⏎A Dark and Stormy Night⏎The story begins, literally, in June 1816 at Villa Diodati overlooking Switzerland’s Lake Geneva. Here,

  6. #6 peak

    ham, Lt. Col. of the 26th Illinois Volunteers. Born in Covington, Kentucky, Tinkham graduated from West Point Academy in 1849, and worked as a civil engineer. He later settled in Homer

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: the truee, not the C: C A: A C: C A: A C: C A: A C: C A: A C: C A: A A

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

    before the destination.⏎I will depart to mine own land. --Num. x. 30.⏎Ere thou from hence depart. --Milton.⏎He which hath no stomach to this fight

  2. #2 peak

    a politician, to look good rather then actually be good. ” to thine own self be true, And it must follow, as the night the day, Thou canst not then be false to any man. Farewell; my blessing season

  3. #3 peak

    thou lettest me steal a loaf, brandy, a hen, a goose, a pig or a horse, I will give thee a big candle, because thou art my sweet little golden God.<|endoftext|>The Hogshooter field, located in

  4. #4 peak

    his first soliloquy in Act 1 Scene 2 where he recognizes that "self-slaughter" is against God's commandment (i.e. Thou shall not kill). Here, Hamlet is being over dramatic: youthful hyperbole

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. L23:415 excites
  2. L20:1391 excites
  3. L18:967 suppresses
  4. L3:2783 suppresses
  5. L6:1927 weakly suppresses
  6. L22:258 weakly suppresses
  7. L22:714 weakly suppresses
  8. L8:1492 weakly suppresses
  9. L0:2159 weakly suppresses
  10. L19:2941 weakly suppresses
  11. L3:187 weakly excites
  12. L3:2540 weakly suppresses
  13. L19:119 weakly suppresses
  14. L20:1074 weakly excites
  15. L0:2999 weakly suppresses
  16. L7:92 weakly suppresses
  17. L16:1543 weakly suppresses
  18. L0:587 weakly excites
  19. L21:2002 weakly excites
  20. L11:223 weakly suppresses
  21. L14:709 weakly suppresses
  22. L2:457 weakly suppresses
  23. L21:2656 weakly suppresses
  24. L2:2645 weakly excites

Feeds later layers

  1. L27:785 weakly suppresses
  2. L25:407 weakly excites
  3. L26:2776 weakly suppresses
  4. L27:2247 weakly excites
  5. L25:2029 weakly excites
  6. L27:763 weakly excites
  7. L25:108 weakly suppresses
  8. L26:1088 weakly excites
  9. L27:545 weakly suppresses
  10. L25:1139 weakly excites
  11. L26:294 weakly suppresses
  12. L25:2596 weakly excites
  13. L26:267 weakly suppresses
  14. L27:720 weakly suppresses
  15. L26:3019 weakly suppresses
  16. L27:1356 weakly excites
  17. L25:457 weakly excites
  18. L25:2499 weakly excites
  19. L25:2274 weakly excites
  20. L25:1895 weakly excites first digit of a year like 2020
  21. L25:2025 weakly excites
  22. L25:125 weakly excites
  23. L26:1353 weakly suppresses
  24. L25:1879 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 -44.38 and -42.371 values between -32.37 and -30.371 values between -30.37 and -28.371 values between -22.37 and -20.373 values between -20.37 and -18.371 values between -18.37 and -16.362 values between -16.36 and -14.361 values between -14.36 and -12.364 values between -12.36 and -10.361 values between -10.36 and -8.366 values between -8.36 and -6.3612 values between -6.36 and -4.3620 values between -4.36 and -2.361131 values between -2.36 and -0.362547 values between -0.36 and 1.6499 values between 1.64 and 3.6429 values between 3.64 and 5.6517 values between 5.65 and 7.6513 values between 7.65 and 9.657 values between 9.65 and 11.655 values between 11.65 and 13.651 values between 13.65 and 15.652 values between 15.65 and 17.652 values between 21.65 and 23.651 values between 33.66 and 35.66offnegativepositiveoften

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. ronics
  2. asses
  3. ró
  4. 鸠
  5. ạm
  6. Sans
  7. cream
  8. lace
  9. ié
  10. فصل

Suppresses

  1. bserv
  2. e
  3. ele
  4. 地上
  5. eus
  6. ulis
  7. ElementType
  8. 新三
  9. ely
  10. esign