Neuron Explorer

Qwen3-0.6B

'seen' after 'never' or 'rarely'

A neuron in layer 0 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 responds to the word 'seen' when it comes after words like 'never', 'rarely', or 'last', as in 'had never seen'. Turning it up did not produce a clear, consistent change in the writing.

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

    of its western relative, the Ivory-Billed Woodpecker. The bird was last seen in 1944, and recently has been declared extinct.⏎A kay

  2. #2 peak

    To be honest, those fruits look like the breasts of a cow. I have never seen this plant in any other country, yet it is hard to imagine something so flashy

  3. #3 peak

    focused on to overcome many of the more frequently seen injuries by orthopaedic therapists. It is these similarities which have encouraged many therapists

  4. #4 peak

    Matt 2008?” video is a great example of the impact of music on images and changes how we look at it.⏎In case you haven’t seen this,

  5. #5 peak

    , to thin the herds. So far, it is working.⏎Contrary to my story, wolves don’t normally attack people. They’re shy animals rarely seen by visitors.⏎Until releases this week from Science Advances, it was believed there were

  6. #6 peak

    spy lots of different kinds of leaves lying on the ground. Some were leaves I had never seen. Some were still green, while others were changing to their autumn colors.⏎Have

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 problem of the old man. I have been thinking about it for a long time. It's a problem. It's a problem. It's a problem. It's a problem. It's a problem. It's a problem.

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

    (reigned 1187–56 bce) who defended his

  2. #2 peak

    (So do we, which is why we laugh at this monk's struggles.)⏎Here

  3. #3 peak

    (GNBDK)⏎Never do to anyone else anything that you would not want someone

  4. #4 peak

    (p. 136) and recognized by Hans Reichelt (pp.

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

None: this is the first layer.

Feeds later layers

  1. L9:785 weakly excites
  2. L4:296 weakly suppresses
  3. L18:611 weakly suppresses
  4. L4:18 weakly suppresses
  5. L17:466 weakly suppresses
  6. L1:110 weakly suppresses
  7. L1:1210 weakly suppresses
  8. L1:2147 weakly suppresses
  9. L6:226 weakly excites
  10. L12:2174 weakly suppresses mixed, web boilerplate phrases
  11. L19:194 weakly suppresses
  12. L18:1078 weakly suppresses
  13. L1:2677 weakly suppresses
  14. L3:574 weakly excites
  15. L17:2489 weakly excites
  16. L7:2660 weakly suppresses
  17. L7:1331 weakly suppresses
  18. L18:1329 weakly suppresses
  19. L4:1701 weakly suppresses
  20. L13:499 weakly suppresses
  21. L1:2461 weakly suppresses
  22. L21:518 weakly suppresses
  23. L21:486 weakly suppresses
  24. L14:2321 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.

2 values between -0.65 and -0.611 values between -0.53 and -0.491 values between -0.49 and -0.452 values between -0.45 and -0.411 values between -0.37 and -0.332 values between -0.33 and -0.296 values between -0.29 and -0.253 values between -0.25 and -0.2119 values between -0.21 and -0.1746 values between -0.17 and -0.13140 values between -0.13 and -0.09312 values between -0.09 and -0.05834 values between -0.05 and -0.011814 values between -0.01 and 0.03460 values between 0.03 and 0.07159 values between 0.07 and 0.1155 values between 0.11 and 0.1524 values between 0.15 and 0.1812 values between 0.18 and 0.227 values between 0.22 and 0.263 values between 0.26 and 0.301 values between 0.30 and 0.341 values between 0.34 and 0.381 values between 0.38 and 0.421 values between 0.82 and 0.861 values between 0.90 and 0.94offnegativepositiveoften

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. elves
  2. ext
  3. 出口
  4. 复苏
  5. iff
  6. 意图
  7. uard
  8. led
  9. umble
  10. spd

Suppresses

  1. verage
  2. -initialized
  3. deltas
  4. те
  5. aye
  6. ólogo
  7. Paginator
  8. اما
  9. NavBar
  10. 持有的