Neuron Explorer

Qwen3-0.6B

'of' after a noun phrase head

A neuron in layer 7 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 word 'of' when it follows a noun like 'set', 'type', 'part', or 'style', as in 'a set of criteria'. Turning it up made the model's text drift into unrelated topics like code and weather, so the steering does not show a clear effect.

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

    full information.)⏎Welcome to English 303: Development of technical writing skills and styles. This course requires a different set of criteria from that used in composition courses, both in teaching and in evaluating students’

  2. #2 peak

    bones and the tailbone (coccyx).⏎- Because this part of the spine bears the weight and stress of the trunk and upper body, the lum

  3. #3 peak

    used type of screw conveyor. Used to convey bulk materials from one part of a process to another

  4. #4 peak

    of Giving to Others⏎Generous Behavior Increases Happiness⏎Not only does giving to others increase their happiness, it also increases our own. Studies amongst different cultures and ages have consistently found that individuals who spend money on others report higher levels of happiness than

  5. #5 peak

    different set of binary codes than Fish and glass of red wine this is how to order food and

  6. #6 peak

    people who have good fitness levels. However, it is best to begin with Ashtanga yoga so you get a sense of how it feels to do that style of yoga. Yoga meditation is an integral part of the daily yoga practice. Yoga meditation

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: what is the name of the place where the two are, the thing that is the universe, and the universe is everything. Let me think of the answer, the place where we are. So, the answer to this is everything. So

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

    American institution, both feared and revered. Sadly, this savage tool that was once used to break the back of my ancestors finds its marks on too many

  2. #2 peak

    , which is vital for exchanging best practices, supporting afforestation events through volunteers from both sides and raising environmental awareness, stressing the urgency of collaboration on this global matter that affects everyone on the island.⏎The CV/AI methods

  3. #3 peak

    are 'lime mix' and 'canal' respectively. Hence it has been suggested that the name may mean a canal built of lime mix.⏎This Karaikal area formed an integral part of the Pallava kingdom in the eighth century(C 7

  4. #4 peak

    1619 and set an example for others to follow. As Virginians migrated in search of new opportunity, they took these lessons of self-rule they had learned and put them into practice in other colonies, territories and states.⏎In

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. L2:725 suppresses
  2. L4:270 suppresses
  3. L3:194 suppresses
  4. L6:1556 suppresses
  5. L2:426 suppresses
  6. L5:2885 suppresses
  7. L5:1350 suppresses
  8. L2:2116 suppresses
  9. L3:1180 excites
  10. L5:2900 suppresses
  11. L3:472 weakly excites
  12. L1:1874 weakly excites
  13. L0:1344 weakly suppresses
  14. L6:2561 weakly excites
  15. L2:579 weakly suppresses
  16. L5:2566 weakly suppresses
  17. L3:1637 weakly suppresses
  18. L4:464 weakly suppresses
  19. L2:2278 weakly suppresses
  20. L6:1467 weakly excites
  21. L1:2925 weakly excites
  22. L6:345 weakly excites
  23. L4:633 weakly excites
  24. L5:1661 weakly excites

Feeds later layers

  1. L9:633 excites
  2. L11:1218 excites
  3. L18:1298 excites
  4. L12:1127 excites
  5. L8:272 excites
  6. L15:1187 excites
  7. L18:1425 excites
  8. L12:2722 excites
  9. L10:2418 excites
  10. L10:739 suppresses
  11. L8:706 excites
  12. L13:1004 excites
  13. L9:2829 excites
  14. L14:2444 excites
  15. L9:516 suppresses
  16. L13:685 excites
  17. L10:1115 excites
  18. L10:2403 excites
  19. L11:199 excites
  20. L14:1060 weakly excites
  21. L8:1137 weakly excites
  22. L13:2554 weakly excites
  23. L12:521 weakly excites
  24. L17:2139 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 -1.75 and -1.651 values between -1.34 and -1.241 values between -1.24 and -1.141 values between -1.14 and -1.032 values between -1.03 and -0.931 values between -0.93 and -0.833 values between -0.83 and -0.723 values between -0.72 and -0.624 values between -0.62 and -0.5223 values between -0.52 and -0.4266 values between -0.42 and -0.31164 values between -0.31 and -0.21425 values between -0.21 and -0.111221 values between -0.11 and -0.011428 values between -0.01 and 0.10342 values between 0.10 and 0.20101 values between 0.20 and 0.3037 values between 0.30 and 0.4121 values between 0.41 and 0.5123 values between 0.51 and 0.615 values between 0.61 and 0.7110 values between 0.71 and 0.825 values between 0.82 and 0.922 values between 0.92 and 1.022 values between 1.02 and 1.136 values between 1.13 and 1.231 values between 1.23 and 1.332 values between 1.33 and 1.431 values between 1.43 and 1.542 values between 1.64 and 1.744 values between 2.26 and 2.36offnegativepositiveoften

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. arity
  2. alent
  3. eel
  4. swana
  5. hape
  6. gain
  7. antage
  8. anse
  9. uality
  10. ategy

Suppresses

  1. ourselves
  2. przec
  3. 让我们
  4. 因为我们
  5. 跟她
  6. 给我们
  7. OnError
  8. 告诉我们
  9. กระบ
  10. -pack