Neuron Explorer

Qwen3-0.6B

the word 'in' after a noun

A neuron in layer 14 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 'in' when it follows a noun and links it to a place, group or field, as in 'disease in modern humans' or 'Professor of Chemistry in the'. Turning it up made the model repeat phrases like 'the problem' or 'the weather is good', so the steering does not clearly reflect this pattern.

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

    most important genealogies are recorded at Matt. 1:1–17 and Luke 3:23–28. These genealogies in the Gospels are essential, for they reveal the family lineage of Christ. Bel

  2. #2 peak

    the equivalence is generated by⏎and it is immediate that every generalized element is equivalent to the universal generalized element ; in spirit, this is the Yoneda lemma in disguise.⏎Now we prove the proposition on colimits of nerves.⏎where is evaluation

  3. #3 peak

    has supported violence, starting with beatings with boots and small⏎weapons, evolving today into a terrorist like cult armed with deadly military⏎weapons.Just like gangs in the U.⏎S. skinheads also fight among each other. These⏎f

  4. #4 peak

    to new biological experiments," said Thomas V. O'Halloran, the study's senior author and the Charles E. and Emma H. Morrison Professor of Chemistry in the Weinberg College of Arts and Sciences at Northwestern. He and geneticist Val

  5. #5 peak

    -and-quartered.⏎The sadistic appetites of this English crowd are similar to those of the French mob in Book 1, chapter 5. The title of the chapter, "A

  6. #6 peak

    Clause is mainly used to improve the performance of the specific query.The Oracle 9i provides the new functionality of With Clause.The with clause is just like temporary tables in oracle.Mainly the with clause is used to execute subqueries in fast way.It

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: if we can, in that way, in that way, in that way, in that way, in that way, in that way, in that way, in that way, in that way, in that way, in that 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

    Radio-telemetric System to Monitor Cardiovascular Function in Rats with Spinal Cord Transection and Embryonic Neural Stem Cell Grafts⏎Institutions: Drexel University College of Medicine, Heidelberg University Hospital, Veterans Administration Medical

  2. #2 peak

    Island.⏎The New Zealand Hydrological Society⏎This article has been published in Journal of Hydrology (NZ). © 1995 The New Zealand

  3. #3 peak

    Short Introductions series from Oxford University Press contains hundreds of titles in almost every subject area. These pocket-sized books are the perfect way to get ahead in a new subject quickly. Our expert authors combine facts, analysis, perspective, new ideas,

  4. #4 peak

    VE Articles!⏎Assessment of Social Cognition in Non-human Primates Using a Network of Computerized Automated Learning Device (ALDM) Test Systems⏎Institutions: Aix-Marseille University.⏎Fag

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. L3:493 suppresses
  2. L11:2207 suppresses "of" after a noun in trademark and title phrases
  3. L4:289 excites
  4. L10:262 suppresses
  5. L4:1966 weakly suppresses
  6. L9:1025 weakly excites
  7. L8:351 weakly suppresses 'in' after 'high' or 'dressed'
  8. L3:128 weakly excites
  9. L2:2132 weakly excites
  10. L13:132 weakly excites "of" after a noun
  11. L0:1984 weakly suppresses
  12. L2:755 weakly excites
  13. L12:1275 weakly suppresses
  14. L6:1633 weakly suppresses
  15. L8:1895 weakly suppresses
  16. L1:1179 weakly suppresses 'in' after 'result' (results in)
  17. L7:1142 weakly excites
  18. L9:2558 weakly excites
  19. L12:1222 weakly suppresses
  20. L0:1144 weakly suppresses
  21. L4:803 weakly excites
  22. L12:1968 weakly excites
  23. L10:314 weakly excites
  24. L13:8 weakly excites

Feeds later layers

  1. L23:1366 excites
  2. L16:1028 excites "in" after a superlative or ordinal
  3. L19:2869 excites
  4. L25:1865 excites 'in' in 'keep in mind'
  5. L19:1345 excites
  6. L17:706 excites
  7. L24:893 suppresses
  8. L19:704 excites
  9. L16:1968 excites
  10. L25:3070 excites
  11. L18:1588 excites
  12. L21:1935 excites
  13. L16:1557 excites 'in' meaning 'in this case' or 'in between'
  14. L22:2653 excites
  15. L16:1830 suppresses
  16. L16:2244 excites
  17. L17:2821 excites
  18. L20:2850 excites
  19. L24:2584 excites 'in' in set phrases like 'in mind'
  20. L24:1957 excites capital 'In' starting a word or name
  21. L16:3007 excites
  22. L17:1434 excites
  23. L24:1312 excites
  24. L20:1574 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.

5 values between -0.91 and -0.7127 values between -0.71 and -0.52261 values between -0.52 and -0.321005 values between -0.32 and -0.131799 values between -0.13 and 0.07595 values between 0.07 and 0.26114 values between 0.26 and 0.4518 values between 0.45 and 0.6514 values between 0.65 and 0.8414 values between 0.84 and 1.037 values between 1.03 and 1.238 values between 1.23 and 1.426 values between 1.42 and 1.621 values between 1.62 and 1.816 values between 1.81 and 2.004 values between 2.00 and 2.201 values between 2.20 and 2.394 values between 2.39 and 2.591 values between 2.59 and 2.782 values between 2.78 and 2.971 values between 2.97 and 3.172 values between 3.17 and 3.361 values between 3.36 and 3.563 values between 3.75 and 3.941 values between 4.14 and 4.331 values between 4.33 and 4.531 values between 4.72 and 4.911 values between 4.91 and 5.112 values between 5.30 and 5.491 values between 6.27 and 6.461 values between 6.46 and 6.661 values between 6.66 and 6.85offnegativepositiveoften

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. context
  2. {}]
  3. =context
  4. .getContext
  5. context
  6. traceback
  7. getContext
  8. ozo
  9. '/',⏎
  10. variants

Suppresses

  1. romo
  2. 架
  3. áz
  4. etta
  5. iture
  6. nable
  7. ration
  8. ро
  9. Soon
  10. nicos