Neuron Explorer

Qwen3-0.6B

unclear: academic boilerplate and code keywords

A neuron in layer 12 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on scattered spots in academic and web text, such as the "JC" in "ASJC Scopus subject areas" and the word "Select" in a database query. There is no single clear pattern, and turning it up did not give a clear theme.

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

    respectful and culturally sensitive manner. Privacy is essential and the nurse must be aware of their own ...⏎You have reached your viewing limit for this book.⏎What people are saying - Write a review⏎Respiratory system 52 Thoracotomy⏎

  2. #2 peak

    of With Clause in oracle. In following section i would like to explain about the syntax as well as multiple examples of with clause.⏎With SQL_Query_Name As⏎Select * from New_SQL_Query_name;⏎Execution of With Clause :⏎In this section i

  3. #3 peak

    the Students from Student table whose marks is more than Average of all marks.⏎(Select Avg(M<|endoftext|>Euler's Equation and the Physical Reality. =. a) Euler's

  4. #4 peak

    h x L g x = = then ( ) lim x c f x exists and is equal to L. Three Special Limits 1. sin lim 1 x x x = 2. 1 cos lim x x x -= 3

  5. #5 peak

    hostilities occur, in part because such efforts will help to address some of the current challenges in space security.⏎By entering this website, you consent to the use of technologies, such as cookies and analytics, to customise content, advertising and provide

  6. #6 peak

    determine how newspaper articles and television reports describe and analyze the event. Use this...⏎6th - 12th English Language Arts CCSS: Adaptable⏎The State of the Union Address⏎Introduce your future voters to the annual State

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 (or) I have been reading about the fact that the journal or you are affiliated with / that is, that includes) that includes) or, I have been talking to a department / that includes / or, 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

    diverse set of controls, as well as in a discontinuity analysis on observations near the borders between anglophone and francophone countries.⏎- Colonial rule⏎ASJC Scopus subject areas⏎- Economics and Econometrics⏎- Organizational Behavior and

  2. #2 peak

    -layer coated, triple-layer coated and graded-index-layer coated samples was performed and compared with experimentally derived films. Good agreement between model and experiment was observed.⏎ASJC Scopus subject areas⏎- Electronic, Optical and Magnetic Materials⏎- Ceramics

  3. #3 peak

    |Number of pages||12|⏎|Journal||Classical and Quantum Gravity|⏎|State||Published - Jul 7 2003|⏎ASJC Scopus subject areas⏎- Physics and Astronomy (miscellaneous)<|endoftext|>Most computer

  4. #4 peak

    two different numbers cant have the same cube). Therefore, by Definition 1, is one-to-one....⏎View Full Document⏎- Spring '09<|endoftext|>part of speech: noun⏎definition 1: an upright line

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. L5:2324 weakly suppresses
  2. L10:2289 weakly excites
  3. L4:168 weakly excites
  4. L1:1599 weakly excites
  5. L3:948 weakly suppresses
  6. L3:1232 weakly excites
  7. L0:1169 weakly suppresses
  8. L3:2553 weakly excites
  9. L5:1828 weakly excites
  10. L2:2299 weakly suppresses
  11. L10:1615 weakly excites
  12. L0:1670 weakly excites
  13. L11:28 weakly excites
  14. L1:994 weakly excites
  15. L5:1781 weakly excites
  16. L11:602 weakly suppresses
  17. L5:86 weakly suppresses
  18. L10:398 weakly suppresses
  19. L4:2166 weakly excites
  20. L11:331 weakly excites
  21. L3:730 weakly suppresses
  22. L1:2659 weakly suppresses
  23. L3:1583 weakly excites
  24. L1:186 weakly excites

Feeds later layers

  1. L14:2050 excites
  2. L16:735 excites
  3. L14:1542 excites
  4. L15:3008 excites
  5. L16:2281 excites
  6. L14:880 excites
  7. L13:616 excites
  8. L13:823 suppresses
  9. L13:2964 excites
  10. L13:798 excites
  11. L13:711 excites
  12. L17:1827 excites
  13. L14:2125 weakly suppresses
  14. L13:89 weakly excites
  15. L15:2582 weakly excites
  16. L16:312 weakly excites
  17. L20:1613 weakly suppresses
  18. L13:2693 weakly excites
  19. L13:907 weakly excites
  20. L13:1173 weakly suppresses
  21. L15:485 weakly excites
  22. L18:73 weakly excites
  23. L13:1581 weakly excites
  24. L16:1119 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 -0.67 and -0.641 values between -0.61 and -0.584 values between -0.52 and -0.494 values between -0.49 and -0.461 values between -0.46 and -0.432 values between -0.43 and -0.399 values between -0.39 and -0.368 values between -0.36 and -0.3319 values between -0.33 and -0.3026 values between -0.30 and -0.2744 values between -0.27 and -0.2463 values between -0.24 and -0.2192 values between -0.21 and -0.18146 values between -0.18 and -0.15183 values between -0.15 and -0.12258 values between -0.12 and -0.09336 values between -0.09 and -0.06425 values between -0.06 and -0.02569 values between -0.02 and 0.01475 values between 0.01 and 0.04354 values between 0.04 and 0.07253 values between 0.07 and 0.10197 values between 0.10 and 0.13143 values between 0.13 and 0.1686 values between 0.16 and 0.1962 values between 0.19 and 0.2252 values between 0.22 and 0.2534 values between 0.25 and 0.2819 values between 0.28 and 0.329 values between 0.32 and 0.3510 values between 0.35 and 0.386 values between 0.38 and 0.415 values between 0.41 and 0.441 values between 0.44 and 0.476 values between 0.47 and 0.501 values between 0.50 and 0.533 values between 0.53 and 0.56offnegativepositiveoften

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. games
  2. programs
  3. 产品的
  4. }while
  5. .Transaction
  6. (round
  7. uards
  8. 各式
  9. てきた
  10. 串

Suppresses

  1. étique
  2. ETO
  3. vette
  4. ético
  5. otics
  6. 苎
  7. affecting
  8. itives
  9. 因为它
  10. shouldReceive