Neuron Explorer

Qwen3-0.6B

summary transition phrases like 'in short'

A neuron in layer 6 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron lights up on words that sum up or wrap up a point, such as 'in short', 'all in all' and 'overall'. Turning it up made the written text drift into unrelated, rambling content, so the steering output doesn't show a clear link to the trigger.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens an email to the maker with the neuron already filled in).

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

    climes has had to wrestle with rapid changes, demands for food, clothing, shelter and fuel, relative scarcity of all these and difficulty of securing them—in short, nearly every possible element in his surroundings which would compel him to get out and

  2. #2 peak

    narrator’s and characters’ voices and which is richly composed of idiom and colloquialism, exclamations, repetitions, and circumlocutions—in short, all the features of a mind instantly verbalizing. In this way, the

  3. #3 peak

    -lost ship. It is believed that the Endurance is located more than two miles (3.2 km) beneath the surface of the ocean.⏎All in all, the team will spend about 45 days in the Southern Ocean, most

  4. #4 peak

    , and its land… In short, every Indian nation is free to adopt its own laws and be ruled by them

  5. #5 peak

    F-22 is perhaps best known for its role in the Global Strike Task Force. Each one costs about $148 million.⏎Needless to say, the F-22 is kind of a big deal. Going head to head

  6. #6 peak

    |⏎|Required to build||libstdc++|⏎|Required to build||fortran|⏎

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 question of how to approach the problem of writing a well-structured and well-organized argument. I know that some people approach the problem of writing a well-structured and well-organized argument. In this case, I have been trying

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

    , 1/4 turn anti-clockwise and then forward 1_______.⏎9. Can you give Pirate Pete directions to find Percy Parrot?⏎Great work, Shipmates! Now Pirate Pete has gathered his things, he is ready to

  2. #2 peak

    acycline resistance was maintained in spite of the declining concentration of tetracycline. (C) 2002 Elsevier Science B.V. All rights reserved.⏎|Publication status||Published - 2002|⏎- whole

  3. #3 peak

    of Scouts BSA.⏎Printable helps for requirements:⏎Get started on your Next Big Thing Nova award with these ideas and related achievements:⏎STEM stands for science, technology, engineering, and mathematics. The NO

  4. #4 peak

    When you have almost any queries concerning wherever along with tips on how to employ online yoga certification, you’ll be able to contact us with our own site. This word is derived the Sanskrit root, yog, which means to combine. Our ultimate

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. L3:542 excites
  2. L5:1004 weakly excites
  3. L4:2058 weakly excites
  4. L5:1143 weakly suppresses
  5. L4:270 weakly suppresses
  6. L4:226 weakly excites
  7. L5:341 weakly excites
  8. L4:567 weakly suppresses
  9. L3:853 weakly suppresses
  10. L5:372 weakly suppresses
  11. L4:773 weakly suppresses
  12. L1:266 weakly excites
  13. L5:1171 weakly suppresses
  14. L3:2068 weakly excites
  15. L5:1550 weakly suppresses
  16. L4:543 weakly suppresses
  17. L4:29 weakly suppresses
  18. L5:1463 weakly excites
  19. L5:3035 weakly suppresses
  20. L5:1771 weakly excites
  21. L4:2515 weakly excites
  22. L4:2286 weakly suppresses
  23. L3:386 weakly excites
  24. L5:326 weakly suppresses

Feeds later layers

  1. L8:510 excites
  2. L9:705 excites
  3. L16:1687 suppresses
  4. L7:1253 excites
  5. L11:3070 weakly excites
  6. L18:2610 weakly excites
  7. L9:40 weakly suppresses
  8. L7:1714 weakly excites
  9. L9:1517 weakly suppresses
  10. L17:1029 weakly suppresses
  11. L13:1734 weakly excites sentence end right before a line break
  12. L7:796 weakly excites
  13. L9:2277 weakly suppresses
  14. L13:2735 weakly excites
  15. L7:181 weakly excites
  16. L9:2459 weakly suppresses
  17. L10:1716 weakly excites
  18. L8:169 weakly excites
  19. L8:960 weakly excites
  20. L13:240 weakly excites
  21. L14:2312 weakly excites
  22. L8:1839 weakly excites
  23. L22:2940 weakly excites
  24. L10:2380 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.

1 values between -1.54 and -1.451 values between -1.37 and -1.281 values between -1.10 and -1.011 values between -0.83 and -0.743 values between -0.74 and -0.656 values between -0.65 and -0.562 values between -0.56 and -0.4714 values between -0.47 and -0.3861 values between -0.38 and -0.29225 values between -0.29 and -0.20535 values between -0.20 and -0.111144 values between -0.11 and -0.021179 values between -0.02 and 0.07446 values between 0.07 and 0.16195 values between 0.16 and 0.2552 values between 0.25 and 0.3419 values between 0.34 and 0.437 values between 0.43 and 0.525 values between 0.52 and 0.611 values between 0.61 and 0.705 values between 0.70 and 0.793 values between 0.79 and 0.881 values between 0.97 and 1.061 values between 1.95 and 2.04offnegativepositiveoften

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. Nationals
  2. -elect
  3. -redux
  4. Examiner
  5. 锦标
  6. fusion
  7. Trot
  8. 给您
  9. | ⏎
  10. @(

Suppresses

  1. ilent
  2. 频
  3. 日消息
  4. akes
  5. ada
  6. UILD
  7. ools
  8. aç
  9. апр
  10. esti