Neuron Explorer

Qwen3-0.6B

'like' after 'feel'

A neuron in layer 1 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 'like' when it comes right after 'feel' or 'feeling', as in 'makes you feel like'. When it was turned up, the model's writing did not visibly change in a way that matches this pattern.

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

    likely to buy the outside brands. If people feel like they have no other choice but to buy the foreign good since it is not available

  2. #2 peak

    your child’s) symptoms may be related to a food allergy or not and can help identify which foods should be avoided to prevent possible allergic reaction⏎If you feel like you or your child has experienced an allergic reaction to foods, call our office to

  3. #3 peak

    ., is an ideal stop. Situated on the banks of the Mississippi River at its most serene and picturesque, this is the kind of town that makes you feel like a<|endoftext|>History of crystallography⏎From Lucretius to Kita

  4. #4 peak

    , and makes you feel like you aren’t in control.⏎Ketamine is FDA-approved for use as a

  5. #5 peak

    mainstream books, not isolated as a separate genre or segregated strand of literature.⏎- aim to keep up to date with matters surrounding diversity and inclusion.⏎If you feel like we could be doing this better than we already are then please don't hesitate to

  6. #6 peak

    and everyone else graduates in skill. "This is really painful and comes up often when I talk to young athletes," says Andersonn. "It makes them feel like failures; they feel deeply humiliated."⏎Parents can be more sensitive to this issue

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 current. I think that the current. I have been thinking about lately. So the current is, I have been thinking about lately. The current is, I have been thinking about lately. So the current, I have been thinking about

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

    . But there’s still a danger in the mountains in the summer.⏎“Initially, dry lightning could be a concern, so obviously, the fire season is looking not so great right now,” he said.⏎Weather data showed the last year’s conditions

  2. #2 peak

    1830. (See etymonline.)⏎Not only did Shakespeare rhyme hour with flower, but he also sometimes spelled them the same.⏎It fears not policy that Hereticke,⏎Which works on leases of short numbred howers

  3. #3 peak

    thus starting a whole host of conspiracy theories.⏎Geologist Dr. Robert Schoch and author John Anthony West made a case that the erosion marks on the Sphinx appears not to be made by wind or sand, but by water, such as falling rain

  4. #4 peak

    hear the daily stats and buzz, but presidential elections are about the big picture — where we want to go and the best way to get there. This means looking not only at political options but also at the way we humans are set up — how

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. L0:148 weakly excites
  2. L0:2643 weakly excites
  3. L0:1730 weakly suppresses
  4. L0:1279 weakly excites
  5. L0:2828 weakly suppresses
  6. L0:1574 weakly excites unclear: mostly line breaks, mixed text
  7. L0:157 weakly suppresses
  8. L0:2966 weakly excites
  9. L0:1301 weakly suppresses
  10. L0:2103 weakly excites
  11. L0:1336 weakly suppresses
  12. L0:2019 weakly suppresses
  13. L0:1224 weakly suppresses
  14. L0:762 weakly excites
  15. L0:2456 weakly suppresses
  16. L0:283 weakly excites
  17. L0:3042 weakly excites
  18. L0:1651 weakly suppresses
  19. L0:1948 weakly suppresses
  20. L0:1588 weakly excites
  21. L0:1130 weakly excites
  22. L0:1110 weakly excites
  23. L0:2073 weakly suppresses
  24. L0:69 weakly suppresses

Feeds later layers

  1. L2:1949 suppresses
  2. L11:2740 weakly suppresses
  3. L6:311 weakly suppresses
  4. L13:2608 weakly excites
  5. L15:1916 weakly excites
  6. L2:1980 weakly excites
  7. L13:1863 weakly excites
  8. L24:1459 weakly excites
  9. L2:2850 weakly suppresses
  10. L15:2289 weakly excites
  11. L19:1726 weakly excites
  12. L2:893 weakly suppresses
  13. L17:1501 weakly excites
  14. L6:2453 weakly excites
  15. L27:1564 weakly suppresses
  16. L8:1214 weakly excites
  17. L15:2961 weakly excites
  18. L19:1879 weakly suppresses
  19. L22:427 weakly suppresses
  20. L3:2877 weakly excites
  21. L16:1644 weakly suppresses
  22. L2:1197 weakly suppresses
  23. L6:1628 weakly suppresses
  24. L18:2284 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 -2.28 and -2.101 values between -2.10 and -1.921 values between -1.92 and -1.743 values between -1.56 and -1.381 values between -1.38 and -1.201 values between -1.20 and -1.012 values between -1.01 and -0.838 values between -0.83 and -0.659 values between -0.65 and -0.4726 values between -0.47 and -0.29425 values between -0.29 and -0.112786 values between -0.11 and 0.07542 values between 0.07 and 0.2563 values between 0.25 and 0.4424 values between 0.44 and 0.627 values between 0.62 and 0.802 values between 0.80 and 0.981 values between 0.98 and 1.162 values between 1.16 and 1.342 values between 1.34 and 1.521 values between 4.78 and 4.96offnegativepositiveoften

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. hek
  2. Iteration
  3. ��
  4. 欠
  5. icolor
  6. idency
  7. BC
  8. '
  9. Beg
  10. 弁

Suppresses

  1. presso
  2. атор
  3. ushima
  4. 溱
  5. Filed
  6. NOTICE
  7. تعالى
  8. Tamb
  9. مية
  10. lửa