Neuron Explorer

Qwen3-0.6B

'as' after 'use' or 'taking' (as a model)

A neuron in layer 17 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 'as' when it says something is used as an example, model, or standard, like 'use them as general guidelines'. Turning it up made the model produce repetitive, loose text, so steering doesn't clearly show this.

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

    STE as technical names and technical verbs). STE gives you the rules and the categories for these technical words. Basically, writers can use the approved words in the dictionary as a core vocabulary. But they can also use terms that are usual in their companies

  2. #2 peak

    where glycemic index comes into the scene. Glycemic index (GI) classifies foods based on how quickly they elevate blood sugar levels, taking pure glucose as the comparison point.⏎Foods with a high GI, such as white bread and

  3. #3 peak

    ous Explorations Through Science and Stories (MESS)⏎Teachers may use this guide and recommended materials as a resource to respond to children’s interest and curiosity as they explore the properties of

  4. #4 peak

    , read across to find your target heart rate. Your maximum heart rate is about 220 minus your age. The figures are averages, so use them as general guidelines.⏎|Age||Target HR Zone 50-85%

  5. #5 peak

    This Title The Easter Rising: Revolution and Irish Nationalism, Second Edtion⏎In this innovative work, Alan Ward uses the pivotal event in twentieth-century Irish history as a prism through which to survey Irish history from the twelfth century to

  6. #6 peak

    and science for every school year group. We really hope that you can use some, or all, of this content as you see fit, whether that’s to compliment, vary or boost work set by

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: you have to be with the code. It's not the code you're doing it on the computer, but you're there there. You have to be with the code. Let this be. Let this be, because you're there.

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

    was literally found at your fingertips. Fingerprints and signatures used to be a trustworthy component of your acceptance or approval – especially in matters concerning finance and law. As the world changes, most of our financial matters have moved seamlessly online. Our digital identity

  2. #2 peak

    of Oregon and Washington. Let's hope Cascadians welcome them back as the agents of ecological restoration that they are.⏎Posted by Eric de Place | Permalink

  3. #3 peak

    . We are pleased to see that learning more about a different form of communication could help us to help patients.<|endoftext|>As the planet warms, China’s wheat crops will be threatened by more frequent epidemics

  4. #4 peak

    While some people and teens are natural planners, most are not. And they may find it challenging to figure out how to “become” a planner.⏎As the saying goes…⏎Without a plan, teens will:⏎- lose time trying to figure

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. L16:1780 suppresses
  2. L10:417 suppresses
  3. L9:1877 suppresses
  4. L3:1233 excites
  5. L6:2593 suppresses
  6. L5:1395 excites
  7. L4:683 excites
  8. L10:132 weakly excites
  9. L5:1998 weakly excites
  10. L10:714 weakly suppresses
  11. L5:165 weakly suppresses
  12. L16:792 weakly excites "the" inside a prepositional phrase
  13. L15:1151 weakly suppresses
  14. L15:232 weakly suppresses
  15. L16:2847 weakly suppresses
  16. L6:2224 weakly excites
  17. L5:2881 weakly suppresses
  18. L3:936 weakly suppresses
  19. L0:2810 weakly excites
  20. L5:1016 weakly excites
  21. L9:319 weakly excites equals signs in maths and equations
  22. L3:470 weakly suppresses
  23. L15:7 weakly suppresses
  24. L8:410 weakly excites

Feeds later layers

  1. L19:1874 excites
  2. L20:1253 excites
  3. L23:916 excites
  4. L19:2656 excites
  5. L19:1815 excites
  6. L22:1204 excites
  7. L19:2531 excites
  8. L19:2511 excites
  9. L20:2244 excites
  10. L19:2638 excites
  11. L19:2450 excites
  12. L26:588 weakly suppresses
  13. L18:1036 weakly excites
  14. L19:2553 weakly excites
  15. L24:2939 weakly excites
  16. L22:2991 weakly excites
  17. L22:684 weakly suppresses
  18. L18:90 weakly excites
  19. L18:144 weakly suppresses
  20. L25:2270 weakly suppresses
  21. L18:2233 weakly suppresses
  22. L21:2805 weakly excites 'the' right before 'subject' or 'source'
  23. L19:1906 weakly excites
  24. L21:1851 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.

541 values between -1.29 and -0.593162 values between -0.59 and 0.10124 values between 0.10 and 0.7927 values between 0.79 and 1.4811 values between 1.48 and 2.176 values between 2.17 and 2.8613 values between 2.86 and 3.551 values between 3.55 and 4.244 values between 4.24 and 4.931 values between 4.93 and 5.621 values between 5.62 and 6.311 values between 6.31 and 7.001 values between 7.00 and 7.691 values between 7.69 and 8.391 values between 8.39 and 9.081 values between 9.08 and 9.772 values between 11.15 and 11.842 values between 11.84 and 12.531 values between 13.91 and 14.601 values between 14.60 and 15.291 values between 15.98 and 16.671 values between 16.67 and 17.361 values between 19.44 and 20.131 values between 21.51 and 22.202 values between 25.65 and 26.34offnegativepositiveoften

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. part
  2. “
  3. follows
  4. follow
  5. ges
  6. ус
  7. “So
  8. 候选人
  9. part
  10. ”

Suppresses

  1. itudes
  2. itude
  3. rium
  4. BufferData
  5. estion
  6. angkan
  7. latina
  8. 经济技术
  9. neighbouring
  10. OrNil