Neuron Explorer

Qwen3-0.6B

unclear: words after 'less than' or 'of'

A neuron in layer 7 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 fires on a mix of words that follow qualifiers like 'under', 'less than', 'women of', or 'developed and', such as 'five' in 'under five' and 'color' in 'women of color'. It is hard to find one clear theme. Turning it up made the text wander into repetitive, unfocused sentences without a clear topic.

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

    forces, a rumour starts to spread according to which NI provided the list to State A and cooperated with State A’s<|endoftext|>Find all elements less than 0 or greater than 10 and replace them with NaN⏎Getting the indices from

  2. #2 peak

    the Peace Corps. He created the Foundation Heart Ventures-Grupo de Ap<|endoftext|>is an elementary subatomic particle with infinitesimal mass⏎(less than 0.3 eV..?) and with no electric charge⏎. Neutrinos

  3. #3 peak

    on troubleshooting a refrigeration system while applying the principles of superheat and subcooling. It may also teach you the proper methods to tackle some typical troubleshooting tasks

  4. #4 peak

    Phillip Newman Specific rights apply.⏎A service of: ASD at NASA / GSFC⏎& Michigan Tech. U.<|endoftext|>Troubleshooting With Superheat, Subcooling⏎You also need to have the right tools and know-how to apply these

  5. #5 peak

    greatest challenges.⏎Roughly 1.7 million children under five years old die every year in India, says Unicef, representing more than

  6. #6 peak

    has closed by less than 20 cents. In 2010, women earned 77 cents on every dollar earned by men. Women of color fared even worse--African American women earned only 67 cents,

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 am a student and I have a question, and I am trying to write this as a blog post. I am writing this, and I have a post with a blog post, and I am writing a post summary. I am a

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

    . Why are we here? What are we supposed to be doing with the time we've been granted? Achilles knew from the beginning that his years would be short, that he was destined to die at Troy, and that his legacy would forge

  2. #2 peak

    , Spain ended diplomatic relations with America and the US Navy established a blockade of Cuba, marking the official start of the Spanish-American War. The war would last less than four months, but saw the downfall of the Spanish Empire and the rise of America

  3. #3 peak

    by periods of quiescence of several months – years long. During quiescent periods, there is very little or no accretion, while during much shorter periods of activity there is an abundant accretion, due probably to disc flow

  4. #4 peak

    disparity. According to BLS data, women are paid 86 percent of the median hourly wages of men. This evaluation accounts for part-time (fewer than 35 hours) workers, which are more often<|endoftext|>Hiding information 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. L4:203 strongly excites
  2. L5:1560 strongly excites
  3. L5:977 excites
  4. L4:1315 suppresses
  5. L6:339 excites
  6. L4:1115 suppresses
  7. L5:2703 suppresses
  8. L4:1877 excites
  9. L6:1879 weakly suppresses
  10. L6:1461 weakly suppresses
  11. L4:661 weakly excites
  12. L5:559 weakly suppresses
  13. L5:938 weakly suppresses
  14. L3:2611 weakly excites
  15. L2:2751 weakly suppresses spiral and screw words
  16. L0:2023 weakly suppresses
  17. L4:2010 weakly excites
  18. L6:1129 weakly suppresses
  19. L4:1075 weakly excites
  20. L5:2328 weakly suppresses
  21. L4:2144 weakly suppresses
  22. L6:1677 weakly excites
  23. L3:2304 weakly suppresses
  24. L3:1402 weakly suppresses

Feeds later layers

  1. L10:2308 strongly suppresses
  2. L13:2869 strongly suppresses
  3. L11:1427 strongly suppresses
  4. L16:1930 suppresses
  5. L8:140 suppresses
  6. L11:1549 suppresses
  7. L11:2703 excites
  8. L11:2994 suppresses
  9. L13:2314 excites
  10. L16:1120 suppresses
  11. L12:455 suppresses
  12. L18:805 suppresses
  13. L8:545 suppresses
  14. L9:1122 suppresses
  15. L9:465 suppresses
  16. L16:1060 excites
  17. L11:1081 suppresses 'first' and 'inaugural' as starting points
  18. L12:1272 excites
  19. L8:1211 suppresses
  20. L19:2011 suppresses
  21. L8:2065 excites
  22. L13:2117 excites
  23. L15:1139 suppresses
  24. L8:1395 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 -3.57 and -3.411 values between -3.24 and -3.072 values between -3.07 and -2.912 values between -2.74 and -2.571 values between -2.57 and -2.411 values between -2.41 and -2.242 values between -2.07 and -1.903 values between -1.90 and -1.743 values between -1.74 and -1.575 values between -1.57 and -1.402 values between -1.40 and -1.242 values between -1.24 and -1.073 values between -1.07 and -0.9010 values between -0.90 and -0.7412 values between -0.74 and -0.5725 values between -0.57 and -0.4051 values between -0.40 and -0.24397 values between -0.24 and -0.072141 values between -0.07 and 0.10984 values between 0.10 and 0.26206 values between 0.26 and 0.4326 values between 0.43 and 0.606 values between 0.60 and 0.768 values between 0.76 and 0.934 values between 0.93 and 1.103 values between 1.10 and 1.271 values between 1.27 and 1.431 values between 1.43 and 1.601 values between 1.60 and 1.772 values between 2.10 and 2.271 values between 2.60 and 2.771 values between 2.93 and 3.10offnegativepositiveoften

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. 持久
  2. 久
  3. Demand
  4. ((__
  5. 万元以上
  6. ibern
  7. obili
  8. undo
  9. ći
  10. 去年

Suppresses

  1. 那么简单
  2. minor
  3. .createComponent
  4. immediate
  5. encers
  6. erture
  7. Ass
  8. aid
  9. ass
  10. minimal