Neuron Explorer

Qwen3-0.6B

"not" in "if not" contrasts

A neuron in layer 10 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 fires on the word "not" (or "less") in set phrases such as "if not most," "if not being taught here" or "much less resolved," where a second, contrasting idea is being added. The negative side is mostly odd punctuation in citations and links. Turning it up made the output repetitive and unrelated.

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

    four or five in their regular government schools. Despite their age, they still don’t know basic math. The toddlers are their siblings, who the girls — if not being taught here — would be taking care of at home, while

  2. #2 peak

    enzel found that restorative but not retributive responses led to greater forgiveness. Taken together, Wenzel’s studies suggest that the offender’s behavior and not his punishment will become the focus.⏎That’s not to say that there’s no

  3. #3 peak

    The center of the retina is called the macula.⏎This is the most sensitive area of the retina used for reading vision and straight-ahead vision. Retinal and specifically macular diseases can cause clouding and distortion of vision, loss of peripheral vision

  4. #4 peak

    member states.⏎The rapid growth of the socio-cultural complexities of society, also triggered by the fast development of scientific thought in the XXI century, in general, and the Internet, in particular, entails a sharp increase of the social diversity. This

  5. #5 peak

    nutritional and / or pharmacological.⏎It is very important to note that in addition to external factors

  6. #6 peak

    the entrepreneurial subject while encouraging a value system that promotes self-interest, if not an unchecked selfishness.1 Since the 1970s, neoliberal

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 first thing to note is that the first thing to do is to realize that if something is... in the context of time. The question is that is, the first thing to do is to realize that the first question is to understand.

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

    Vitamin C and Immune Function, 2017, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5707683/#:~:text=It%20is%20a%2

  2. #2 peak

    -53. http://dx.doi.org/10.1080/13527266.2011.620764⏎BELK, R. (201

  3. #3 peak

    2017)⏎|Council of Trent|⏎|Accepted by||Catholic Church|⏎|Fifth Council of the Lateran (1512–1517)|⏎|First Vatican Council (1869–

  4. #4 peak

    oietin in the brain improves exercise performance in mice without inducing erythropoiesis. FASEB J. doi:10.1096<|endoftext|>Valentine’s Day Task Cards (2nd – 4th Grade)⏎

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. L9:880 suppresses
  2. L8:2127 excites
  3. L7:1156 suppresses
  4. L9:2892 suppresses
  5. L8:1680 weakly suppresses
  6. L8:803 weakly suppresses
  7. L7:2107 weakly excites
  8. L7:1846 weakly suppresses
  9. L5:1924 weakly suppresses
  10. L1:2725 weakly suppresses
  11. L8:2839 weakly excites
  12. L2:2302 weakly suppresses
  13. L1:2093 weakly suppresses
  14. L8:1023 weakly excites
  15. L2:1537 weakly excites
  16. L8:2617 weakly suppresses
  17. L8:911 weakly suppresses
  18. L5:778 weakly suppresses
  19. L9:2936 weakly suppresses
  20. L1:2664 weakly suppresses
  21. L7:2906 weakly suppresses
  22. L3:1212 weakly suppresses
  23. L1:1825 weakly excites
  24. L7:498 weakly suppresses

Feeds later layers

  1. L16:2578 excites
  2. L14:1102 weakly excites
  3. L20:1707 weakly excites
  4. L13:2356 weakly excites
  5. L15:1699 weakly excites
  6. L14:1763 weakly excites
  7. L24:1091 weakly excites
  8. L13:1757 weakly excites
  9. L18:2305 weakly suppresses
  10. L12:1443 weakly excites opening parenthesis after a name or term
  11. L26:2098 weakly suppresses
  12. L25:1341 weakly suppresses
  13. L16:2746 weakly suppresses
  14. L14:853 weakly excites
  15. L12:1034 weakly excites
  16. L15:752 weakly suppresses
  17. L14:651 weakly excites
  18. L14:2308 weakly excites
  19. L16:2719 weakly suppresses
  20. L14:268 weakly excites
  21. L15:3004 weakly excites
  22. L15:1474 weakly excites
  23. L14:439 weakly excites
  24. L14:1963 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 -2.04 and -1.841 values between -1.84 and -1.643 values between -1.24 and -1.042 values between -1.04 and -0.842 values between -0.84 and -0.6440 values between -0.64 and -0.44483 values between -0.44 and -0.241591 values between -0.24 and -0.041464 values between -0.04 and 0.16238 values between 0.16 and 0.3633 values between 0.36 and 0.5617 values between 0.56 and 0.759 values between 0.75 and 0.958 values between 0.95 and 1.154 values between 1.15 and 1.351 values between 1.35 and 1.552 values between 1.75 and 1.951 values between 2.35 and 2.552 values between 2.55 and 2.751 values between 2.75 and 2.952 values between 3.15 and 3.341 values between 3.74 and 3.941 values between 4.54 and 4.741 values between 5.73 and 5.93offnegativepositiveoften

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. まり
  2. 会被
  3. ecessarily
  4. its
  5. Periph
  6. igidBody
  7. malink
  8. /releases
  9. OrDefault
  10. forced

Suppresses

  1. �建
  2. �数
  3. uja
  4. бит
  5. CATEGORY
  6. 她是
  7. オー
  8. ´t
  9. 蒽
  10. ships