Neuron Explorer

Qwen3-0.6B

unclear: metadata labels and closing quotes

A neuron in layer 13 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 is hard to pin down. It fires most on the word "By" in a catalogue entry for who deposited a document, and on some document breaks, but these cases look unrelated. Turning it up or down did not produce a clear theme.

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

    that will give a useful input to those interested in Artificial Intelligence in education.⏎|Subjects:||L Education > L Education (General)|⏎|Deposited By:||Zaidatun Tasir|⏎|Deposited On:||

  2. #2 peak

    :⏎A = epsilon.c.l⏎Where A is the absorbance measurement at a given wavelength⏎epsilon is the extinction coefficient in M^-1.cm^-1⏎c is the concentration of the material in mol.dm^-3 (molar)⏎l

  3. #3 peak

    to large step sizes.⏎- Scott E. Fahlman: An Empirical Study of Learning Speed in Back-Propagation Networks, September 1988<|endoftext|>Cardio and weight

  4. #4 peak

    a base for cultivating other.⏎The spawn is used for transferring mycelium onto any material from which mushrooms will grow, called a substrate. There are plenty of substrates, straw, cardboard, logs, and wood chips; these are some best

  5. #5 peak

    +ΦV) 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

  6. #6 peak

    ⏎- Warn others when passing⏎- Keep dogs on a leash at all times for their protection, and for yours⏎- Respect all wildlife encountered on the trail<|endoftext|>In 1847, when Mormon pioneers arrived in the Salt Lake Valley

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 current period, and the current period of the current period. In the current period. The current period refers to the current period. The current period refers to the current period. The current period refers to the current period. The current period

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

    Richard Feynman, and one of his most memorable quotes explains that “Science is the belief in the ignorance of the experts.”⏎Indeed, the “experts” of science are so often wrong that it makes their arrogance laughable, and today

  2. #2 peak

    study published in the journal Aggressive Behavior supports the idea that perfectionism may develop in a social group and suggests that indirect aggression triggers it. The "aggressor" talks behind a person's back<|endoftext|>You are using an outdated and unsupported browser.⏎

  3. #3 peak

    It is as if Mill began with the harm principle in mind, then concocted a description of liberty to justify it. The “devil,” in this case, lies not in the details but in the harm principle:⏎That principle is, that

  4. #4 peak

    he?⏎He delays. We know he can. No doubt. We pray he will, realizing he may not.⏎Struggling with delayed answers? Maybe those delayed answers are to

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. L8:901 suppresses
  2. L9:2212 suppresses
  3. L11:324 excites
  4. L7:1893 weakly suppresses
  5. L12:2455 weakly suppresses
  6. L11:2750 weakly excites
  7. L11:2187 weakly excites
  8. L12:2672 weakly excites
  9. L7:1870 weakly excites
  10. L11:143 weakly suppresses
  11. L8:440 weakly excites
  12. L12:221 weakly excites
  13. L12:285 weakly excites
  14. L11:2085 weakly excites
  15. L6:1071 weakly suppresses
  16. L7:1267 weakly suppresses
  17. L7:1265 weakly suppresses
  18. L8:1129 weakly excites
  19. L2:291 weakly excites
  20. L11:526 weakly excites
  21. L3:158 weakly suppresses
  22. L11:2087 weakly suppresses
  23. L0:868 weakly excites
  24. L6:2985 weakly suppresses

Feeds later layers

  1. L15:2362 suppresses
  2. L14:1843 suppresses
  3. L14:1038 suppresses
  4. L14:1660 suppresses
  5. L16:2833 suppresses
  6. L15:2319 suppresses
  7. L20:2755 suppresses
  8. L15:617 excites
  9. L14:2766 suppresses
  10. L18:992 suppresses
  11. L14:353 suppresses
  12. L20:470 suppresses
  13. L19:1638 suppresses
  14. L14:1989 suppresses
  15. L16:1554 suppresses
  16. L21:765 suppresses
  17. L15:2787 suppresses
  18. L14:1558 suppresses
  19. L14:1839 suppresses
  20. L14:2786 suppresses
  21. L14:2653 excites
  22. L14:995 suppresses
  23. L14:696 suppresses
  24. L14:2947 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 -1.81 and -1.731 values between -1.65 and -1.581 values between -1.58 and -1.504 values between -1.34 and -1.274 values between -1.19 and -1.112 values between -1.03 and -0.961 values between -0.96 and -0.883 values between -0.88 and -0.802 values between -0.80 and -0.723 values between -0.72 and -0.655 values between -0.65 and -0.575 values between -0.57 and -0.499 values between -0.49 and -0.4119 values between -0.41 and -0.3432 values between -0.34 and -0.2677 values between -0.26 and -0.18214 values between -0.18 and -0.11448 values between -0.11 and -0.03980 values between -0.03 and 0.05826 values between 0.05 and 0.13621 values between 0.13 and 0.20362 values between 0.20 and 0.28181 values between 0.28 and 0.3669 values between 0.36 and 0.4424 values between 0.44 and 0.5110 values between 0.51 and 0.591 values between 0.59 and 0.671 values between 0.82 and 0.902 values between 1.21 and 1.29offnegativepositiveoften

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. ותר
  2. рес
  3. ongan
  4. ButtonModule
  5. urses
  6. しかない
  7. ivre
  8. 都不敢
  9. evin
  10. vẻ

Suppresses

  1. 指的是
  2. 是指
  3. Ston
  4. "?
  5. Immigration
  6. referred
  7. referring
  8. refers
  9. '?
  10. diam