Neuron Explorer

Qwen3-0.6B

ampersand joining two items

A neuron in layer 19 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 lights up on the "&" symbol when it joins two things in a title or list, like "Backstage, & Offstage". It goes quiet or negative on the word "and" in phrases like "by and large". Turning it up made the output wander into unrelated text, so the steering doesn't reveal much.

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

    by Dunn & Price)⏎Also see posts: “Adult Learning styles“⏎Existential – these thinkers are focused on issues too deep for other kids to understand, & may be prone to depression as they ponder the meaning of life. Careers involving philosophy

  2. #2 peak

    lesson plans or texts, but in schematic form, suggesting avenues along which the conversation might develop.<|endoftext|>Introduction to Production⏎Creating Theatre Onstage, Backstage, & Offstage⏎Introduction to Production: Creating Theatre Onstage, Backstage, &

  3. #3 peak

    , courgettes⏎3. WHEN? (see crop chart)⏎Right time: temperature, how long til harvest? Seed packets will tell you when to sow &

  4. #4 peak

    ⏎• High levels of task commitment (motivation)⏎• High levels of creativity⏎EXP: Many gifted students find logical reasoning to be their preferred learning style, & for others linguistics may be (Language Arts & Math are not automatically synonymous –

  5. #5 peak

    IS, CURE, PREVENTION - home - CONTENTS: Analysis of small paint samples provides the history of paint layers & colors on buildings & can diagnose the cause of paint failures - How to diagnose the

  6. #6 peak

    Net = hardware (servers, routers, switches, wires, etc.) + the TCP/IP protocol, which makes the data stored on the web servers available to you & me (.. via the URL, entered into your browser-of-choice).⏎Not sure

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: I have a 3/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or/or

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

    contain that have been useful in research.⏎The glands are enclosed in a capsule of and internally divided into . Blood vessels and nerves enter the glands at the and gradually branch

  2. #2 peak

    465<|endoftext|>“.. modern science seems to have exploded into a multitude of highly specialised areas and distinct disciplines that may at times be interconnected, but that by and large ignore one another. There appears to be an overwhelming trend toward a proliferation of

  3. #3 peak

    about the progression and flow of my lectures. I believe that students tend to get sort of tired and space out a bit if a lecture on any topic goes on and on in the same way, so I try to work in changes and transitions that

  4. #4 peak

    be 850, 845, 840, 835, 830, 825 and on and on! On our Number of the Day chart we also look for patterns. We

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. L13:131 excites 'and' joining parallel phrases
  2. L4:57 suppresses
  3. L9:92 suppresses "and" or "or" joining two items
  4. L1:1250 suppresses
  5. L10:74 excites
  6. L0:2146 suppresses
  7. L16:376 suppresses 'or' joining alternatives
  8. L0:313 excites "and" joining paired nouns
  9. L8:70 excites 'and' between stacked superlatives
  10. L15:78 excites
  11. L4:1330 suppresses
  12. L18:868 suppresses 'and' joining two nouns in a pair
  13. L15:82 suppresses
  14. L15:114 weakly excites
  15. L17:2782 weakly excites 'same' in 'at the same time'
  16. L15:115 weakly excites
  17. L18:569 weakly excites
  18. L15:122 weakly suppresses
  19. L16:99 weakly suppresses
  20. L2:75 weakly suppresses
  21. L3:50 weakly excites
  22. L18:131 weakly suppresses
  23. L0:114 weakly suppresses
  24. L15:80 weakly suppresses

Feeds later layers

  1. L26:1007 strongly suppresses
  2. L22:198 suppresses
  3. L20:885 suppresses 'and' joining paired words
  4. L22:1739 suppresses 'and' starting a place or person name
  5. L24:205 excites
  6. L20:2386 suppresses
  7. L26:2490 suppresses
  8. L25:1694 suppresses 'and' joining paired names or fields
  9. L23:2015 weakly suppresses
  10. L25:1008 weakly suppresses
  11. L26:347 weakly excites the 're' in self-reliant and similar
  12. L23:1185 weakly excites
  13. L25:120 weakly suppresses
  14. L22:262 weakly excites comma inside big numbers
  15. L22:791 weakly excites
  16. L26:513 weakly excites
  17. L21:173 weakly excites
  18. L24:124 weakly excites dollar sign before a money amount
  19. L27:172 weakly excites
  20. L26:729 weakly excites
  21. L25:3035 weakly suppresses
  22. L22:2880 weakly suppresses
  23. L21:571 weakly suppresses
  24. L20:1009 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.

1 values between -35.00 and -33.741 values between -28.68 and -27.423 values between -24.89 and -23.632 values between -23.63 and -22.373 values between -22.37 and -21.102 values between -21.10 and -19.842 values between -19.84 and -18.584 values between -18.58 and -17.317 values between -17.31 and -16.057 values between -16.05 and -14.7914 values between -14.79 and -13.529 values between -13.52 and -12.268 values between -12.26 and -11.007 values between -11.00 and -9.736 values between -9.73 and -8.478 values between -8.47 and -7.217 values between -7.21 and -5.952 values between -5.95 and -4.682 values between -3.42 and -2.1610 values between -2.16 and -0.892956 values between -0.89 and 0.37843 values between 0.37 and 1.641 values between 1.64 and 2.901 values between 10.48 and 11.741 values between 11.74 and 13.011 values between 14.27 and 15.53offnegativepositiveoften

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. 发展
  2. 技术支持
  3. 社会
  4. 和支持
  5. 发展模式
  6. 社会发展
  7. 服务质量
  8. 社会稳定
  9. 和个人
  10. 技术和

Suppresses

  1. /or
  2. 煦
  3. thus
  4. ROID
  5. 蔼
  6. 小编一起
  7. /OR
  8. 珅
  9. rogen
  10. therefore