Neuron Explorer

Qwen3-0.6B

"of" after a measure like inches or teaspoon

A neuron in layer 12 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

Lights up on "of" right after a measurement or portion word, such as "an inch of", "a teaspoon of" or "several inches of". Turning it up made the output wander into repeated fragments that did not match the prompts.

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

    later blooms, sow them after the last frost date.⏎- If you are planting seeds, sow them directly in the ground, covering them with about ¼ inch of soil. Space them 8 to 18 inches apart, depending on the

  2. #2 peak

    a class in Java? Local variables − Variables defined inside methods, constructors or blocks are called local variables. Classes define the behavior for objects of its type. Instances of the class Class represent classes and interfaces in a running Java application. If we do

  3. #3 peak

    Oxide 0.4% Sulphur Dioxide 0.4%; Phosphorous Oxide 0.3%.⏎Take about one teaspoon of food-grade diatomaceous earth with liquid once

  4. #4 peak

    Vietnamese. The division of Cham into Western and Phan Rang Cham immediately followed the Vietnamese overthrow of the last Cham polity. Each uses a distinct variety of the script, although the former are mostly Muslim and now prefer to use the Arabic alphabet

  5. #5 peak

    sitting in muddy soil or in an area where water is pooled on top of the soil.⏎Mulch around the base of outdoor gardenia shrubs with several inches of organic material

  6. #6 peak

    , but the name Mohs chemosurgery continues to be associated with the procedure now correctly termed Mohs Micrographic Surgery.⏎After the removal of the visible portion of the tumor by excision or curettage (debulking), there are

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 need to do a question for a report. You can find the link to the article in the link. But since I'm not sure about the answer, I just need to make sure. So, the user wants to put in 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

    concerned and demonstrates their free, prior and informed consent;⏎- R.5: A large number of local manifestations of the element are inscribed on the National List of Intangible Cultural Heritage administered by the Department of Intangible Cultural Heritage of the Ministry

  2. #2 peak

    one-to-one functions. DEFINITION A function is called a one-to-one function if it never takes on the same value twice; that is, If a horizontal line intersects the graph of in more than one point, then we see from Figure

  3. #3 peak

    (at least to Physicists!) experiment, Galileo went to the top of the leaning tower of Pisa and dropped a wooden ball and a lead ball, both the same size

  4. #4 peak

    Red List of Threatened Species.⏎The ocean is the bloodstream of mother earth. The Artery

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. L10:1395 excites
  2. L9:1428 excites
  3. L10:469 suppresses 'of' after a noun phrase
  4. L11:579 suppresses
  5. L9:463 excites
  6. L6:3070 excites
  7. L11:153 suppresses
  8. L8:1003 suppresses "the" or "of" before a noun phrase
  9. L5:453 suppresses
  10. L8:502 excites
  11. L8:892 excites
  12. L10:1364 weakly excites
  13. L11:601 weakly suppresses
  14. L8:1212 weakly excites
  15. L6:1557 weakly excites
  16. L5:1721 weakly excites
  17. L6:2217 weakly suppresses
  18. L8:526 weakly suppresses
  19. L9:592 weakly excites
  20. L4:1686 weakly excites
  21. L5:363 weakly excites
  22. L1:664 weakly suppresses
  23. L8:1755 weakly suppresses
  24. L9:393 weakly suppresses

Feeds later layers

  1. L16:2530 excites
  2. L16:1216 suppresses
  3. L16:961 excites
  4. L14:2107 excites
  5. L14:1971 excites
  6. L19:1503 excites
  7. L15:632 excites
  8. L13:1781 excites
  9. L13:486 excites
  10. L15:1028 excites
  11. L16:1077 excites
  12. L20:956 excites
  13. L17:663 excites
  14. L16:719 excites
  15. L16:2612 excites
  16. L13:1997 excites
  17. L15:404 suppresses
  18. L14:1508 excites
  19. L13:1906 excites
  20. L14:1707 excites
  21. L14:1901 excites
  22. L17:1241 excites
  23. L16:408 excites 'of' after a quantity or container noun
  24. L13:602 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 -1.65 and -1.502 values between -1.50 and -1.346 values between -1.19 and -1.045 values between -1.04 and -0.8812 values between -0.88 and -0.7318 values between -0.73 and -0.5738 values between -0.57 and -0.4299 values between -0.42 and -0.27327 values between -0.27 and -0.112060 values between -0.11 and 0.041027 values between 0.04 and 0.20219 values between 0.20 and 0.3545 values between 0.35 and 0.5022 values between 0.50 and 0.667 values between 0.66 and 0.815 values between 0.81 and 0.973 values between 0.97 and 1.122 values between 1.12 and 1.274 values between 1.27 and 1.431 values between 1.43 and 1.581 values between 1.74 and 1.891 values between 2.81 and 2.971 values between 3.12 and 3.281 values between 3.74 and 3.891 values between 4.35 and 4.51offnegativepositiveoften

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. 谋
  2. tactic
  3. pter
  4. 정도
  5. quent
  6. ami
  7. assumption
  8. ولد
  9. of
  10. CRM

Suppresses

  1. isée
  2. مل
  3. 茬
  4. neau
  5. iddle
  6. €�
  7. 呛
  8. isseur
  9. itore
  10. 让她