Neuron Explorer

Qwen3-0.6B

unclear: 'of' after a quantity noun

A neuron in layer 8 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 mostly fires on the word 'of' after nouns that describe an amount or group, such as 'a ball of roots' or 'a set of', but the examples are mixed and some are unrelated. Turning it up gave unrelated text, so the steering result adds little.

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

    resources to learn more about Caddo history and culture, https://scholarworks.sfasu.edu/cgi/viewcontent.cgi?article=4012&context=ita⏎Visit the THC’s Learning Resource page for home-related lesson plans

  2. #2 peak

    Tree?⏎When pruning the roots of your bonsai, the first step is to remove it from its pot and use a root hook to disentangle its ball of roots.⏎Then, remove as much of the soil as you can with your fingers

  3. #3 peak

    risk for sepsis.⏎They surveyed stool samples from 14 patients with long ICU stays, including six people who stayed more than a month. Using next-generation sequencing of the microbes’ ribosomal RNA 16S subunit, the

  4. #4 peak

    |⏎|Listener||Contains a method that handles an event|⏎|Entity||Data object with identity (ID), for example “User”|⏎|Collection||Set of data objects|⏎|Value Object||Data object without identity, for example “Date

  5. #5 peak

    were gone."⏎Join to answer this question⏎Join a community of thousands of dedicated teachers and students.Join eNotes<|endoftext|>Is there something else you would

  6. #6 peak

    Oregon town of Hammond, near the mouth of the Columbia. He’s taking a boatful of customers into shallow water to hook sturgeon.⏎“If you drop off the ledge just

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: questions. I have been thinking about how to questions to get a job. I have been thinking about a question to get a job, and I have found a job. I am a life partner that I have a living job. I have

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

    a time, it seemed like myrtle spurge was a solid choice for “water-wise” gardens. The plant grows well in shade, requires little in the way of hydration, grows in disturbed environments, and looks attractive. But myrtle sp

  2. #2 peak

    : "We watched trucks unload sacks of flour into crowds that hadn't eaten in three days. I can still see Schim [sic], a wisp of a man, standing on the jeep silhouetted against the darkling sky quietly

  3. #3 peak

    a survivorship program designed to educate children and their families about the challenges they may face as childhood cancer survivors -- has awarded $125,000 in college scholarships to 38 cancer survivors.⏎To learn more about the<|endoftext|>The

  4. #4 peak

    , questions and answers of programming and scripting languages:<|endoftext|>RALEIGH — New research has found that North Carolina’s shellfish industry provides over $27 million in economic impact and 532 jobs in the state. Until 20

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. L6:2862 suppresses
  2. L7:1208 suppresses
  3. L6:2366 excites
  4. L6:2593 suppresses
  5. L6:1407 suppresses
  6. L6:398 excites
  7. L7:2164 suppresses period inside country abbreviations
  8. L6:1789 suppresses
  9. L6:1410 excites
  10. L6:2873 weakly suppresses
  11. L2:686 weakly excites
  12. L6:458 weakly suppresses
  13. L7:2414 weakly excites
  14. L1:847 weakly excites
  15. L6:1041 weakly excites
  16. L5:1403 weakly excites
  17. L4:2085 weakly excites
  18. L6:2635 weakly excites
  19. L4:1567 weakly suppresses
  20. L6:2224 weakly excites
  21. L6:1767 weakly suppresses
  22. L5:1982 weakly excites
  23. L6:2785 weakly excites
  24. L6:1892 weakly excites

Feeds later layers

  1. L10:167 suppresses
  2. L14:1240 suppresses
  3. L19:663 suppresses
  4. L14:1913 suppresses
  5. L17:985 suppresses
  6. L12:1561 suppresses
  7. L17:1241 suppresses
  8. L18:77 suppresses
  9. L12:1916 suppresses
  10. L20:2519 suppresses "of" after quantity nouns (millions of, amount of)
  11. L13:1659 weakly suppresses
  12. L14:2510 weakly suppresses
  13. L14:312 weakly excites
  14. L19:2711 weakly suppresses
  15. L13:1370 weakly suppresses
  16. L13:330 weakly excites
  17. L15:537 weakly suppresses middle digits of numbers
  18. L16:1122 weakly suppresses
  19. L15:1386 weakly excites prepositions after passive verbs
  20. L11:810 weakly excites
  21. L13:975 weakly suppresses
  22. L17:199 weakly excites
  23. L12:2680 weakly excites
  24. L20:337 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 -7.50 and -7.251 values between -3.65 and -3.391 values between -3.39 and -3.141 values between -2.88 and -2.621 values between -2.62 and -2.361 values between -2.11 and -1.852 values between -1.85 and -1.594 values between -1.59 and -1.3410 values between -1.34 and -1.087 values between -1.08 and -0.8214 values between -0.82 and -0.5759 values between -0.57 and -0.31907 values between -0.31 and -0.052464 values between -0.05 and 0.21396 values between 0.21 and 0.4629 values between 0.46 and 0.723 values between 0.72 and 0.982 values between 0.98 and 1.231 values between 1.23 and 1.492 values between 1.49 and 1.751 values between 2.26 and 2.521 values between 2.52 and 2.78offnegativepositiveoften

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. Sheet
  2. INET
  3. 这位
  4. 性强
  5. ATORY
  6. 族自治州
  7. eneg
  8. aire
  9. IGATION
  10. istine

Suppresses

  1. wdx
  2. òng
  3. fuels
  4. быт
  5. ymi
  6. 缢
  7. ewitness
  8. 年来
  9. cura
  10. 篑