Neuron Explorer

Qwen3-0.6B

'on' after pressure or strain verbs

A neuron in layer 8 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 fires on the word 'on' when it comes right after phrases like 'put strain on', 'place pressure on' or 'put demand on', where something is being loaded or stressed. When it was turned up, the model's writing drifted toward talk about pressure and stress on things, though the steered text was often repetitive.

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

    DISCS⏎The entire spinal cord is sensitive due to the surrounding nerves. A herniated disc usually causes chronic back pain because of the extra pressure and stress put on the back. Patients ultimately need to rest the body and the spine;<|endoftext|>F

  2. #2 peak

    reintroduced the<|endoftext|>Jogging is a well known activity that can have hazardous effects on the knee while running on pavement. A tremendous amount of strain is placed on the knee when running on a hard surface, like asphalt or pavement. While city

  3. #3 peak

    of the database rather than re-generating it from scratch. The result is that hundreds of queries are replaced with one single query, thereby significantly lightening the load on the web server.⏎I assume it’s

  4. #4 peak

    , and weaker scar tissue sometimes replaces muscular tissue in these cases. Obesity, lack of use, heavy lifting, chronic cough, and chronic constipation place additional pressures on the pelvic floor. Genetically weak collagen, and smoking (which weakens collagen

  5. #5 peak

    and contributing factor to plantar fasciitis. Whether you are gaining body fat, muscle mass, or healthy weight from pregnancy, the added pounds put extra strain on your feet. This can cause plantar fasciitis for the first time,

  6. #6 peak

    problem so that the spark plugs can ignite the proper mixture.⏎3) Engine Drags⏎Whenever you increase the load of your vehicle, it will put more demand on the engine to

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 a new idea about the use of a special type of coin. The price is higher. I have a special type of coin. I have a new idea. The price is higher. The price is higher. The price is higher

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

    to be used as a concrete set accelerator⏎- No flocculation or coagulation⏎- All concretes and mortar containing steel reinforcement, post-tensioned concrete, concrete in contact with chlorides, parking structures, piers,

  2. #2 peak

    the source code and object file is located at sub folder similar to your project name, the executable file is under sub folder debug.⏎Using Borland C++ Compiler Command Line Tools⏎- Installing and running the

  3. #3 peak

    C = Classes (swim lessons and CPR)⏎- D = Devices (personal flotation devices (PFD’s), life jackets, and rescue tools)⏎A = Adult Supervision⏎Drowning is a leading cause of unintentional death in Sacramento County

  4. #4 peak

    launched to the International Space Station (ISS). Samples from Prof. Christian Betzel’s research group at Universität Hamburg will be aboard to be analyzed in the absence of gravity.⏎The experiment in the context of the CUI research is expected to be conducted

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. L6:2663 excites
  2. L4:2351 excites
  3. L7:2901 excites
  4. L5:1683 excites
  5. L7:2849 weakly excites
  6. L7:2435 weakly suppresses
  7. L6:2496 weakly suppresses
  8. L4:1235 weakly excites
  9. L6:2986 weakly suppresses
  10. L5:2745 weakly suppresses
  11. L6:946 weakly excites
  12. L7:2218 weakly suppresses
  13. L6:3066 weakly suppresses
  14. L7:1877 weakly excites
  15. L6:1652 weakly suppresses
  16. L3:1064 weakly suppresses
  17. L7:1538 weakly excites
  18. L7:2612 weakly excites
  19. L4:1753 weakly suppresses
  20. L6:2154 weakly excites
  21. L4:2439 weakly suppresses
  22. L5:1494 weakly suppresses
  23. L3:1185 weakly excites
  24. L0:311 weakly suppresses

Feeds later layers

  1. L10:1079 excites
  2. L11:993 excites
  3. L23:2958 excites
  4. L9:664 suppresses
  5. L10:2602 excites
  6. L23:1750 excites
  7. L10:2024 excites
  8. L12:2994 excites
  9. L10:274 weakly suppresses
  10. L19:2877 weakly excites
  11. L9:1473 weakly excites
  12. L20:3012 weakly excites
  13. L10:2919 weakly excites
  14. L20:2641 weakly excites
  15. L9:1807 weakly excites unclear: mixed, health lists and 'weight'
  16. L23:1954 weakly suppresses
  17. L11:2206 weakly suppresses
  18. L12:2169 weakly excites
  19. L11:749 weakly excites
  20. L11:1737 weakly suppresses
  21. L15:2011 weakly excites
  22. L20:2246 weakly excites
  23. L23:2345 weakly excites
  24. L10:1207 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 -0.78 and -0.665 values between -0.66 and -0.5331 values between -0.53 and -0.41136 values between -0.41 and -0.28461 values between -0.28 and -0.161131 values between -0.16 and -0.041374 values between -0.04 and 0.09563 values between 0.09 and 0.21140 values between 0.21 and 0.3430 values between 0.34 and 0.469 values between 0.46 and 0.587 values between 0.58 and 0.715 values between 0.71 and 0.831 values between 0.83 and 0.962 values between 0.96 and 1.081 values between 1.08 and 1.201 values between 1.20 and 1.332 values between 1.33 and 1.453 values between 1.45 and 1.581 values between 1.58 and 1.701 values between 1.70 and 1.821 values between 1.82 and 1.951 values between 4.06 and 4.18offnegativepositiveoften

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. lict
  2. …)
  3. 减轻
  4. 慰
  5. hana
  6. undue
  7. licted
  8. 负荷
  9. eted
  10. ARY

Suppresses

  1. order
  2. po
  3. 告诉他
  4. .PREFERRED
  5. cheme
  6. ício
  7. erior
  8. posable
  9. flag
  10. riages