Neuron Explorer

Qwen3-0.6B

"to" in "referred to"

A neuron in layer 1 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 "to" in phrases like "referred to as" or "often referred to", where a term is being named or explained. Turning it up made the writing repetitive and oddly circular, which does not clearly relate to this phrase.

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

    60 and Goguryeo in 668. Thereafter, Unified Silla or Later Silla, as it is often referred to, occupied most of the Korean Peninsula, while the northern part re-emerged as

  2. #2 peak

    of DNA by combining existing nucleotides with new bases, creating new types of DNA molecules called DNA-based polymers. The DNA-based polymers, often referred to as designer genes, are used in a variety of ways to produce new proteins,

  3. #3 peak

    America with a mass market media campaign through the<|endoftext|>KAA Gent is often referred to by its second name: the Buffalos. At every match, you will

  4. #4 peak

    is?⏎You might have come across this term “cobots” while searching for a solution to improve your production processes but weren’t quite sure what the term referred to. As you’ve probably noticed yourself, cobots are trending more and more in

  5. #5 peak

    being.⏎What is blood cholesterol? Also referred to simply as cholesterol, blood cholesterol refers to how much of a lipid (fat)

  6. #6 peak

    are often referred to as early stage and late stage.⏎Many asthma sufferers who inhale an allergen

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 way to the way of thinking, the way of thinking, the way of thinking... so I have been thinking about lately... the way of thinking... the way of thinking... the way of thinking... the way of thinking... the way

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

    matter, such as compost. It thrives in full sun but will tolerate part shade.⏎To get the highest yield of tender and flavorful leaves, pinch the tip of each branch, starting in early summer when the plants are 6" tall,

  2. #2 peak

    conomic and moral rights⏎- Guarantee control over the work.⏎- Guarantee remuneration for work through selling or licensing.⏎- They are transferable.⏎- Right of attribution - the right to claim the authorship.⏎- Right of integrity - the

  3. #3 peak

    , & entrepreneurship all in one contest⏎Receive a FREE Maker-Kit full of inventing supplies from Picoturbine of $200 value (Limit of 3 per school) & a $200 Stipend for your

  4. #4 peak

    complete this third step by drawing the legs and the arms as shown in the illustration below.⏎On top of the head, draw antennas using broken lines. The tip of both antennas is made from a small

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. L0:1224 weakly suppresses
  2. L0:178 weakly suppresses
  3. L0:778 weakly excites
  4. L0:24 weakly excites
  5. L0:1301 weakly suppresses
  6. L0:2738 weakly suppresses
  7. L0:516 weakly excites
  8. L0:2030 weakly suppresses
  9. L0:774 weakly suppresses
  10. L0:1987 weakly suppresses
  11. L0:486 weakly suppresses
  12. L0:664 weakly excites
  13. L0:2209 weakly suppresses
  14. L0:139 weakly excites
  15. L0:2579 weakly suppresses
  16. L0:150 weakly excites
  17. L0:1839 weakly excites
  18. L0:785 weakly suppresses
  19. L0:781 weakly excites
  20. L0:2818 weakly suppresses
  21. L0:2375 weakly excites
  22. L0:1481 weakly excites
  23. L0:60 weakly excites
  24. L0:78 weakly excites the 'S' in 'U.S.'

Feeds later layers

  1. L16:1088 suppresses 'of' after a noun phrase, as in 'of course'
  2. L15:785 suppresses 'of' in set phrases like 'of course'
  3. L19:715 suppresses
  4. L17:1835 suppresses
  5. L13:132 weakly suppresses "of" after a noun
  6. L14:1519 weakly suppresses
  7. L17:317 weakly suppresses 'of' after a noun phrase
  8. L4:4 weakly suppresses
  9. L17:385 weakly suppresses
  10. L7:790 weakly suppresses
  11. L3:315 weakly suppresses 'of' after a noun phrase
  12. L5:1207 weakly suppresses 'of' after abstract nouns
  13. L7:2458 weakly suppresses
  14. L6:371 weakly excites
  15. L22:229 weakly suppresses "of" after a noun in "X of Y"
  16. L17:1177 weakly suppresses
  17. L16:2194 weakly suppresses
  18. L2:506 weakly excites
  19. L15:2562 weakly excites
  20. L9:2264 weakly suppresses 'of' after superlatives and 'the X of'
  21. L3:712 weakly suppresses unclear: 'of' after a noun
  22. L17:2234 weakly suppresses
  23. L2:1274 weakly suppresses
  24. L6:1121 weakly suppresses 'while' joining two clauses after a comma

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 -2.46 and -2.381 values between -2.12 and -2.032 values between -1.94 and -1.852 values between -1.85 and -1.772 values between -1.77 and -1.684 values between -1.68 and -1.595 values between -1.59 and -1.514 values between -1.42 and -1.338 values between -1.24 and -1.165 values between -1.16 and -1.073 values between -1.07 and -0.984 values between -0.98 and -0.902 values between -0.90 and -0.817 values between -0.81 and -0.724 values between -0.72 and -0.636 values between -0.63 and -0.556 values between -0.55 and -0.465 values between -0.46 and -0.3713 values between -0.37 and -0.2963 values between -0.29 and -0.20274 values between -0.20 and -0.11934 values between -0.11 and -0.031654 values between -0.03 and 0.06725 values between 0.06 and 0.15143 values between 0.15 and 0.2418 values between 0.24 and 0.326 values between 0.32 and 0.411 values between 0.50 and 0.592 values between 0.67 and 0.761 values between 0.85 and 0.932 values between 0.93 and 1.02offnegativepositiveoften

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. izedName
  2. 秕
  3. aved
  4. 被打
  5. 又被
  6. mojom
  7. ning
  8. 会发生
  9. ифика
  10. 主义者

Suppresses

  1. erto
  2. odal
  3. lio
  4. erw
  5. 行列
  6. satisfaction
  7. 资产负债
  8. olia
  9. erta
  10. śli