Neuron Explorer

Qwen3-0.6B

'of' after a quantity or container noun

A neuron in layer 16 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 'of' when it follows a amount or piece word, like 'instances of', 'amount of', 'one part of', or 'scrap of'. It is quieter, or pushed negative, on 'per' in rates such as 'deaths per year'. Turning it up made the text wander without a clear theme.

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

    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

  2. #2 peak

    , but not in all.⏎A local conservation law is usually expressed mathematically as a continuity equation, a partial differential equation which gives a relation between the amount of the quantity and the "transport" of that quantity. It states that the amount

  3. #3 peak

    followed by the object name, and use the keyword new: Create an object called "myObj" and print the value of x: You can create multiple objects of one class: You can also create

  4. #4 peak

    inators x pollination per pollinator – total pollination⏎Pollinator loss due to human influence could be compensated for by an increase in the number of individuals of remaining species, called numerical compensation. Alternatively species loss could be made up for not

  5. #5 peak

    ilohertz (kHz) passive integrated transponder (PIT) tag. Twenty subadults of each species were implanted with short-term (3 month) acoustic telemetry tags to examine

  6. #6 peak

    a dhoti?⏎Dhoti-wearing men and women in⏎southern India frequently accessorize their traditional garment with a spare⏎scrap of cloth, called an angavastram. The garment is designed to be worn

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: when I have a new project, the time I have a new project, the time I have a new project, the time I have a new project, the time I have a new project, the time I have a new project, the

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

    with blood or tissues of infected animals such as a cough or a bite. However, the CDC says that there is now only an average of seven human plague cases per year and the WHO says the mortality rate is estimated to be between 8-

  2. #2 peak

    health and safety falls under the enormous umbrella of public health.⏎More proof that public health is awesome:⏎- On average, 42,000 deaths per year are prevented among children who receive recommended childhood vaccines .⏎- Diabetes is the leading

  3. #3 peak

    affects some 8.1 women per 100,000 each year. However, it disproportionately affects Latinas (11.1 per 100,000) and African American women (10.

  4. #4 peak

    914-1919 stand at 1,300, which accounts for about 8% of the total population, one man out of every six. This war is held to have ended in 1919

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. L14:1901 suppresses
  2. L12:2757 excites "of" after a measure like inches or teaspoon
  3. L15:1634 excites
  4. L15:894 excites
  5. L15:1283 excites
  6. L12:1869 excites
  7. L13:527 suppresses
  8. L15:331 excites
  9. L10:1235 suppresses
  10. L14:539 weakly excites
  11. L14:655 weakly excites
  12. L15:765 weakly excites
  13. L10:272 weakly suppresses
  14. L11:1039 weakly suppresses
  15. L2:2800 weakly excites
  16. L11:2273 weakly excites
  17. L15:2096 weakly excites
  18. L12:1801 weakly suppresses
  19. L15:2395 weakly suppresses
  20. L8:1254 weakly excites
  21. L14:1639 weakly excites "and" joining two nouns
  22. L12:1020 weakly suppresses
  23. L15:614 weakly excites
  24. L14:245 weakly excites

Feeds later layers

  1. L18:1046 excites
  2. L17:1687 excites
  3. L21:1572 excites
  4. L19:2291 excites
  5. L18:1728 excites
  6. L19:1379 suppresses
  7. L17:2587 suppresses
  8. L17:827 weakly excites
  9. L17:1113 weakly suppresses
  10. L19:590 weakly excites
  11. L17:1040 weakly suppresses
  12. L19:2720 weakly excites
  13. L20:1807 weakly excites
  14. L17:2722 weakly excites
  15. L18:2058 weakly excites
  16. L17:3070 weakly suppresses
  17. L20:1497 weakly excites
  18. L18:1477 weakly suppresses
  19. L24:575 weakly suppresses
  20. L17:3003 weakly suppresses
  21. L20:2161 weakly suppresses
  22. L19:2062 weakly excites
  23. L19:759 weakly excites
  24. L19:2048 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.

2 values between -3.61 and -3.401 values between -2.98 and -2.771 values between -2.56 and -2.351 values between -2.35 and -2.141 values between -2.14 and -1.933 values between -1.93 and -1.721 values between -1.72 and -1.515 values between -1.51 and -1.304 values between -1.30 and -1.0915 values between -1.09 and -0.8824 values between -0.88 and -0.6756 values between -0.67 and -0.46136 values between -0.46 and -0.25833 values between -0.25 and -0.042056 values between -0.04 and 0.17387 values between 0.17 and 0.38144 values between 0.38 and 0.5984 values between 0.59 and 0.8045 values between 0.80 and 1.0133 values between 1.01 and 1.2224 values between 1.22 and 1.428 values between 1.42 and 1.6318 values between 1.63 and 1.849 values between 1.84 and 2.054 values between 2.05 and 2.261 values between 2.26 and 2.472 values between 2.47 and 2.683 values between 2.68 and 2.893 values between 2.89 and 3.101 values between 3.10 and 3.311 values between 3.73 and 3.941 values between 3.94 and 4.151 values between 4.57 and 4.78offnegativepositiveoften

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. ElementType
  2. _formats
  3. 藜
  4. 电价
  5. infer
  6. infer
  7. ItemType
  8. entityType
  9. Rivers
  10. FileType

Suppresses

  1. 干部职工
  2. isode
  3. is
  4. UAL
  5. iset
  6. experiments
  7. veces
  8. 个
  9. 工作会议
  10. MERCHANTABILITY