Neuron Explorer

Qwen3-0.6B

verbs of finding out or thinking

A neuron in layer 12 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 responds to verbs like 'know', 'believe', 'find out', 'think' and 'track' when they lead into a clause or object. Its weaker negative side fires on words like 'about' and 'of' after verbs of talking. The steering results did not show a clear theme when turned up.

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

    a topic or thesis into a logical order. Outlines arrange major topics, subtopics, and supporting details. Writers use outlines when writing their papers in order to know which topic to cover in what order.⏎What is outline

  2. #2 peak

    More Info... by email⏎Consumer ethnocentrism is a psychological concept that refers to individuals who believe that their country's products are superior to those of other countries. This concept also

  3. #3 peak

    rial polyps. The first test is a transvaginal ultrasound. This is done vaginally using a wand-like device that emits sound waves to create a picture of the uterus. If the patient has any polyps, the ultrasound will detect

  4. #4 peak

    know how EGT1 helps roots to overcome gravity. For this, the researchers looked at the genes disrupted in the EGT1 mutant. This, it turned out, were genes for producing parts of the cell wall. This disruption translated into less

  5. #5 peak

    , 1975⏎- The Exxon Valdez, 1994⏎Using the Internet, in a limited period of time, students find out:⏎1. What

  6. #6 peak

    may be due in part to the hormonal upheavals that occur during the teen years. But be careful – it’s easy for adults to take this information and think “it’s just hormones” and therefore think the depression does not need to be

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 have a 3D model of a 3D model of a 3D model of a 3D model of a 3D model of a 3D model of a 3D model of a 3D

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

    the letters we use so often. The earliest forms of writing evolved because members of ancient civilizations needed more efficient ways to express themselves. Listen to this story to hear about the origins of individual letters, as well as learn about the connection between shape and

  2. #2 peak

    ne Davis, works as a Postdoctoral research fellow in the Plant and crop science department at the University of Nottingham.⏎We asked her about the role of women and girls in science and how the situation has changed over the

  3. #3 peak

    not niche. They are not elective or historical. They reach right into those classrooms, affecting every single student. Students we worked with talked of being cat-called, harassed, objectified, condescended to and, most

  4. #4 peak

    to further engage conversation.⏎Vocabulary lists are used in almost every classroom and rarely offer any interactive engagement for students. Join us as we talk about Thinglink, a website that allows students to create<|endoftext|>Pulley Reef (

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. L11:1774 excites
  2. L10:653 excites
  3. L11:2537 excites
  4. L10:2275 suppresses
  5. L9:2247 suppresses
  6. L11:1469 excites
  7. L9:2172 excites
  8. L9:761 excites 'sure' in 'are you sure' phrasing
  9. L9:1512 suppresses
  10. L10:1236 weakly excites
  11. L9:512 weakly excites
  12. L10:2208 weakly excites
  13. L11:1036 weakly excites
  14. L9:2377 weakly suppresses
  15. L11:1715 weakly suppresses
  16. L5:2877 weakly excites
  17. L10:551 weakly suppresses
  18. L8:2209 weakly excites
  19. L10:1941 weakly suppresses
  20. L11:783 weakly excites
  21. L11:1292 weakly excites
  22. L10:2032 weakly excites
  23. L4:1366 weakly excites
  24. L4:666 weakly suppresses the digit 0 in dates

Feeds later layers

  1. L14:1091 excites
  2. L13:743 excites
  3. L16:1019 suppresses
  4. L17:1296 excites
  5. L16:1344 excites
  6. L17:2038 suppresses
  7. L14:1385 excites
  8. L16:2210 weakly suppresses
  9. L20:27 weakly suppresses
  10. L14:421 weakly suppresses
  11. L14:2651 weakly excites
  12. L13:1933 weakly suppresses
  13. L21:655 weakly suppresses
  14. L13:1851 weakly excites
  15. L15:598 weakly excites
  16. L18:317 weakly suppresses
  17. L17:2784 weakly excites
  18. L19:290 weakly suppresses
  19. L18:1027 weakly suppresses
  20. L16:2184 weakly excites
  21. L15:2105 weakly suppresses
  22. L14:1894 weakly excites
  23. L13:1046 weakly excites 'in' or 'on' ending a phrase
  24. L16:457 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 -2.28 and -2.181 values between -1.97 and -1.861 values between -1.65 and -1.551 values between -1.44 and -1.335 values between -1.23 and -1.124 values between -1.12 and -1.026 values between -1.02 and -0.916 values between -0.91 and -0.815 values between -0.81 and -0.709 values between -0.70 and -0.6028 values between -0.60 and -0.4935 values between -0.49 and -0.3959 values between -0.39 and -0.28153 values between -0.28 and -0.18467 values between -0.18 and -0.071886 values between -0.07 and 0.03787 values between 0.03 and 0.14210 values between 0.14 and 0.2483 values between 0.24 and 0.3556 values between 0.35 and 0.4627 values between 0.46 and 0.5623 values between 0.56 and 0.6714 values between 0.67 and 0.7713 values between 0.77 and 0.883 values between 0.88 and 0.987 values between 0.98 and 1.092 values between 1.09 and 1.198 values between 1.19 and 1.302 values between 1.30 and 1.401 values between 1.40 and 1.511 values between 1.51 and 1.613 values between 1.72 and 1.821 values between 1.82 and 1.93offnegativepositiveoften

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. afen
  2. específico
  3. -packages
  4. 津
  5. ้อน
  6. ython
  7. 某一
  8. essim
  9. CONSEQUENTIAL
  10. cpy

Suppresses

  1. ARING
  2. fore
  3. ffect
  4. ieve
  5. .fm
  6. whel
  7. mere
  8. 임
  9. 广场
  10. LETE