Neuron Explorer

Qwen3-0.6B

unclear: qualifiers like 'only' and 'alone'

A neuron in layer 14 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on words that qualify or contrast a claim, such as 'only', 'alone', 'anyone' or 'while', in the middle of an argument. It is hard to pin down more precisely. Turning it up produced rambling text with no clear theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    2. No other industry can directly impact local economies to the same extent as manufacturing.⏎Women’s inclusion in the manufacturing industry is pivotal to sustaining this success. Women only hold roughly

  2. #2 peak

    their designs, software and tutorials online and calling it a day: Just because something is available in theory doesn’t automatically make it accessible to all. (Linux, anyone?)⏎Like a whole cadre of other prosthetic researchers and makers, they are interested

  3. #3 peak

    Establishing a program of incentives and penalties is not enough, alone, however. Enforceability is important—the market alone can’t make improvements permanent. Questions also remain as to how long the greenhouse gas

  4. #4 peak

    users from accessing “valid” content (blocking them from using their devices) and also opened up security holes.⏎Intellectual property should be respected (the digital world runs on it) but we should not do so at the expense of privacy or security

  5. #5 peak

    Unfortunately, due to our continued poisoning of the environment and the Fukushima power plant meltdown, many fish are now loaded with unsafe levels of mercury and radiation. All fish, every single fish on this planet, have some level of mercury; however, some

  6. #6 peak

    Mike Fortes to encourage countries to consider the values of seagrass when managing coastal environments.⏎This has been called the Bolinao Declaration and reads:⏎We, participants of the third International Seagrass Biology Workshop (ISBW 3),

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: I have been thinking about the different things, the different things, the different things. The different things, the different things, the different things, the different things, the different things, the different things, the different things, the different things

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

    Now, your shoes can not only count your steps but also study them.⏎“This means that now you can understand how your feet are being placed on the ground, how much pressure is being applied on the bones, the angle of your steps and more

  2. #2 peak

    of english⏎teachers is going to be english⏎enrichment rather than teaching english⏎to beginners. The ability to teach someone a language with its expressions, its metaphors and its cultural and historical context is not only a large proposition but also

  3. #3 peak

    and Testing. Though they’re closely related, they are, ultimately, different.⏎If you work in the IT industry, you’ve probably come across them. You’ve also probably noticed that many executives – and customers – don’t understand the difference between

  4. #4 peak

    your wheels because you don’t even know where to start.⏎I’ve said this before and I’ll say it again: Teens have SO much going on! So much earlier than we had to. College prep, varsity sports, volunteer work/community

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. L13:1180 suppresses
  2. L10:1459 suppresses
  3. L13:1066 suppresses
  4. L12:982 excites
  5. L12:990 suppresses
  6. L12:690 excites
  7. L8:891 weakly excites
  8. L11:1251 weakly excites
  9. L13:557 weakly excites
  10. L10:1164 weakly excites
  11. L13:1897 weakly suppresses
  12. L10:782 weakly suppresses
  13. L10:2953 weakly excites
  14. L13:2710 weakly suppresses
  15. L10:713 weakly suppresses
  16. L12:107 weakly excites
  17. L4:22 weakly suppresses
  18. L3:1641 weakly suppresses
  19. L7:1656 weakly excites
  20. L13:1296 weakly excites
  21. L13:912 weakly suppresses
  22. L1:2954 weakly suppresses
  23. L13:1193 weakly excites
  24. L2:2900 weakly suppresses

Feeds later layers

  1. L16:2442 excites
  2. L16:2329 suppresses
  3. L17:1099 suppresses
  4. L15:270 suppresses
  5. L19:1605 suppresses
  6. L15:1949 suppresses
  7. L17:632 suppresses unclear: coordinating words in lists
  8. L16:1475 suppresses
  9. L15:2050 suppresses
  10. L17:919 suppresses
  11. L15:2862 suppresses
  12. L15:709 suppresses
  13. L15:732 suppresses
  14. L26:347 suppresses the 're' in self-reliant and similar
  15. L15:509 suppresses
  16. L25:6 excites
  17. L15:132 excites
  18. L16:1141 suppresses
  19. L15:2369 suppresses
  20. L15:1207 weakly suppresses
  21. L19:164 weakly excites
  22. L15:1504 weakly excites
  23. L15:1339 weakly suppresses
  24. L15:1681 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 -5.04 and -4.881 values between -4.24 and -4.092 values between -2.82 and -2.662 values between -2.66 and -2.501 values between -2.50 and -2.341 values between -2.34 and -2.181 values between -2.18 and -2.033 values between -2.03 and -1.873 values between -1.87 and -1.713 values between -1.71 and -1.555 values between -1.55 and -1.398 values between -1.39 and -1.238 values between -1.23 and -1.0812 values between -1.08 and -0.9218 values between -0.92 and -0.7629 values between -0.76 and -0.6032 values between -0.60 and -0.44101 values between -0.44 and -0.28430 values between -0.28 and -0.132250 values between -0.13 and 0.03831 values between 0.03 and 0.19104 values between 0.19 and 0.3537 values between 0.35 and 0.5113 values between 0.51 and 0.676 values between 0.67 and 0.831 values between 0.83 and 0.982 values between 0.98 and 1.143 values between 1.14 and 1.30offnegativepositiveoften

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. inction
  2. 报复
  3. 转载请
  4. '}}
  5. .SuspendLayout
  6. 唛
  7. betr
  8. iller
  9. '}}⏎
  10. ']]⏎

Suppresses

  1. and
  2. 、
  3. 和
  4. 和社会
  5. otional
  6. ,
  7. ~,
  8. icios
  9. 以及
  10. 和服务