Neuron Explorer

Qwen3-0.6B

unclear: asymptotes and electron loss or gain

A neuron in layer 10 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 is mixed. It fires on the word 'asymptotes' in graphing lessons and on some web boilerplate, and it goes negative on 'lose' or 'gain' when electrons are described in chemistry. Turning it up or down did not give a clear theme in the generated 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

    (this will throw an Error in a future version of PHP) in /home/commons/public_html/wp-content/plugins/ultimate-google-analytics/ultimate_ga.php on line 524⏎GUJHS. 2007 March;

  2. #2 peak

    general shape of your graph so that you have a nice place to start.⏎To sketch the full parent graph of cotangent, follow these steps:⏎Find the vertical asymptotes so you can find the domain.⏎Because cotangent is the quotient of cosine

  3. #3 peak

    (in Central America)|⏎|Scientific Name||Lampropeltis triangulum gaigeae|⏎|Conservation Status||Not listed by IUCN|⏎When these snakes are young,

  4. #4 peak

    like with tangent. However, these asymptotes occur whenever the⏎The cotangent parent graph repeats every pi units. Its domain is based on its vertical asymptotes: The first one comes at 0 and then repeats every pi radians.

  5. #5 peak

    (carmelite) [x] st. terasea of the little flower [x] the st. francis [x] [Add Your Own Tags]⏎* Works in the collection are moved off view for many different reasons. Although

  6. #6 peak

    of the year, occurs every year between July 17 and August 24. The shower tends to peak around August 9-13. These meteor showers are really interesting to see, however if you live in an urban area being

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: This is a good article, this is a good article, and this is a good article. I have been thinking about, this is a good article, and this is a good article, and this is a good article. This is 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

    configuration. The Alkali metals and Alkaline earth metals have one and two valence electrons (electrons in the outer shell) respectively. These elements lose electrons to form bonds easily, and are thus very reactive. These elements are the

  2. #2 peak

    almost never react, since they have eight valence electrons, which makes it very stable. The halogens, directly to the left of the noble gases, readily gain electrons and react with metals. The s and p blocks make up the main-group

  3. #3 peak

    1.176-1.709) and vomiting (p < 0.001, OR = 1.969, 95% CI = 1.618-2

  4. #4 peak

    10-10 m? Which of the following orbital designations are incorrect: 1s, 1p, 7d, 9s, 3f, 4f,

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. L9:879 weakly excites
  2. L7:648 weakly excites
  3. L9:1015 weakly suppresses
  4. L5:2741 weakly excites
  5. L5:1015 weakly excites
  6. L2:35 weakly excites
  7. L0:16 weakly excites
  8. L9:1969 weakly excites
  9. L7:58 weakly suppresses
  10. L4:449 weakly suppresses
  11. L6:1011 weakly suppresses
  12. L1:2342 weakly excites
  13. L1:2864 weakly excites
  14. L8:1864 weakly excites
  15. L9:2678 weakly excites
  16. L5:1923 weakly excites
  17. L8:2299 weakly excites
  18. L4:1429 weakly suppresses
  19. L7:940 weakly suppresses
  20. L0:180 weakly excites
  21. L1:267 weakly suppresses
  22. L3:2974 weakly excites
  23. L2:876 weakly suppresses
  24. L4:1690 weakly excites

Feeds later layers

  1. L12:1854 suppresses
  2. L11:2019 weakly suppresses
  3. L24:1193 weakly suppresses
  4. L19:2997 weakly suppresses
  5. L12:2260 weakly excites
  6. L20:2808 weakly suppresses
  7. L11:703 weakly excites
  8. L23:2555 weakly suppresses
  9. L22:1282 weakly excites
  10. L13:1389 weakly suppresses
  11. L24:2547 weakly excites
  12. L14:2354 weakly suppresses
  13. L22:231 weakly suppresses
  14. L12:653 weakly suppresses
  15. L17:2618 weakly excites
  16. L23:431 weakly suppresses
  17. L12:1979 weakly suppresses
  18. L18:430 weakly suppresses
  19. L23:1241 weakly suppresses
  20. L24:1802 weakly excites
  21. L19:1960 weakly suppresses
  22. L25:2072 weakly excites
  23. L19:1757 weakly excites
  24. L11:2880 weakly excites

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 -1.51 and -1.461 values between -0.69 and -0.643 values between -0.64 and -0.583 values between -0.58 and -0.533 values between -0.53 and -0.4712 values between -0.47 and -0.4231 values between -0.42 and -0.3653 values between -0.36 and -0.31121 values between -0.31 and -0.25230 values between -0.25 and -0.20360 values between -0.20 and -0.14498 values between -0.14 and -0.09564 values between -0.09 and -0.03674 values between -0.03 and 0.02471 values between 0.02 and 0.08353 values between 0.08 and 0.13216 values between 0.13 and 0.19156 values between 0.19 and 0.2480 values between 0.24 and 0.3035 values between 0.30 and 0.3521 values between 0.35 and 0.4013 values between 0.40 and 0.466 values between 0.46 and 0.512 values between 0.51 and 0.571 values between 0.62 and 0.68offnegativepositiveoften

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. .every
  2. Cad
  3. หลาย
  4. ably
  5. ';";⏎
  6. 一顿
  7. 루
  8. ఆ
  9. fully
  10. cps

Suppresses

  1. uhn
  2. icons
  3. ought
  4. zer
  5. idi
  6. rence
  7. ники
  8. avier
  9. ZW
  10. 松弛