Neuron Explorer

Qwen3-0.6B

the word 'entry' in reference text

A neuron in layer 12 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron responds to the word 'entry' when it means a dictionary or encyclopedia entry, and to similar phrases like 'post to' or 'search for' that point at a written item. Turning it up made the model drift into repetitive, loosely related text.

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

    the phrase has shifted since then, referring not to patrons and their clients, but 'a collective political preference exercised by a particular interest group'. See also the entry in Wikipedia, which adds that the meaning of Srinivas' expression was first

  2. #2 peak

    , Third Edition,⏎published by Thomas Nelson, 1897. Public Domain, copy freely.⏎Bibliography InformationEaston, Matthew George. "Entry for Tamarisk". "Easton

  3. #3 peak

    direct from Amazon (22% off) Amazon page|⏎|Call number||QC7.H62 2005|⏎|External links||This entry has no external links. Add one.|⏎|Through your library||Configure|⏎

  4. #4 peak

    dose is 15 mg/kg, 5 times daily for 5 days.⏎Best of luck---⏎Search for questions⏎Still looking for answers? Try searching for what you seek or ask your own question.⏎Posted 31 Aug 2

  5. #5 peak

    use, masterpieces of calligraphic art were produced, e.g., the Irish Book of Kells (8th cent.; Trinity College, Dublin; see under Ceanannus Mór) and the English Lindisfarne Gospels

  6. #6 peak

    the dictionary. Looking at the entry, it seems that Mr. Fresh was a bit of a lexical trail-blazer

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 other three, but this is the end of the other three... but this is the end of the other three... but this is the end of the other three... but this is the end of the other three... but this is 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

    Rare Disorders⏎NINDS progressive multifocal leukoencephalopathy information page. National Institute of Neurological Disorders and Stroke website. Available at http://www.ninds.nih.gov/disorders/pml/pml.htm. Updated February 1

  2. #2 peak

    24 16:52:29 EST 2010⏎On Wednesday 24 November 2010 22:12:37, Russ Abbott wrote:⏎> Cool. I wasn't

  3. #3 peak

    network connection. Here are the steps to create an ad hoc network in Windows 7.⏎- Click on Start (Windows icon) and type wireless. Click on Manage wireless networks.⏎- Click on Add to add a network.⏎- Click on Create

  4. #4 peak

    Select General >> Empty Project and type in the project name.⏎- Under folder Source, right-click Select Add >> New Item.⏎- Under Code, Select C++ File (.cpp), however, when you type in the name use a program name with

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. L11:2022 excites
  2. L10:1534 suppresses
  3. L10:176 weakly excites
  4. L6:1331 weakly excites
  5. L10:2521 weakly suppresses
  6. L11:1073 weakly excites
  7. L9:2985 weakly suppresses
  8. L10:2017 weakly excites
  9. L1:768 weakly suppresses
  10. L2:2075 weakly excites
  11. L7:1836 weakly excites
  12. L2:2027 weakly suppresses
  13. L7:1263 weakly excites
  14. L5:2645 weakly suppresses
  15. L4:382 weakly excites
  16. L9:2311 weakly suppresses
  17. L3:362 weakly excites
  18. L10:2980 weakly suppresses
  19. L9:602 weakly excites
  20. L4:982 weakly suppresses
  21. L6:69 weakly suppresses
  22. L3:600 weakly excites
  23. L7:1827 weakly suppresses
  24. L7:2156 weakly suppresses

Feeds later layers

  1. L15:2436 suppresses 'out of' in ratios and rankings
  2. L14:2007 excites
  3. L16:701 suppresses
  4. L17:867 excites unclear: punctuation before an explanation
  5. L16:2299 excites
  6. L17:2405 weakly excites
  7. L14:1423 weakly suppresses
  8. L23:2561 weakly suppresses
  9. L18:1701 weakly excites
  10. L14:1204 weakly suppresses
  11. L16:630 weakly excites
  12. L17:828 weakly suppresses
  13. L15:2741 weakly suppresses
  14. L13:486 weakly excites
  15. L14:1728 weakly suppresses "of" after a numbered section or title
  16. L13:2135 weakly suppresses
  17. L19:2453 weakly excites
  18. L16:2016 weakly suppresses
  19. L13:2310 weakly suppresses
  20. L17:2770 weakly suppresses
  21. L15:291 weakly suppresses
  22. L22:2477 weakly excites
  23. L18:2361 weakly excites
  24. L13:1405 weakly suppresses

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 -1.28 and -1.182 values between -1.18 and -1.092 values between -0.99 and -0.902 values between -0.90 and -0.801 values between -0.71 and -0.614 values between -0.61 and -0.5113 values between -0.51 and -0.4221 values between -0.42 and -0.3278 values between -0.32 and -0.23245 values between -0.23 and -0.13775 values between -0.13 and -0.031926 values between -0.03 and 0.06565 values between 0.06 and 0.16157 values between 0.16 and 0.2558 values between 0.25 and 0.3529 values between 0.35 and 0.4511 values between 0.45 and 0.547 values between 0.54 and 0.642 values between 0.64 and 0.732 values between 0.73 and 0.832 values between 0.83 and 0.931 values between 1.02 and 1.122 values between 1.12 and 1.212 values between 2.46 and 2.56offnegativepositiveoften

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. dedicate
  2. pee
  3. pped
  4. agnostics
  5. homelessness
  6. 련
  7. Propagation
  8. ##
  9. reeze
  10. 一个职业

Suppresses

  1. iev
  2. amongst
  3. IEL
  4. among
  5. antal
  6. among
  7. agal
  8. Tale
  9. iset
  10. ity