Neuron Explorer

Qwen3-0.6B

'on' introducing a location or surface

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 lights up on the word "on" when it says where something is, such as "printed on elastic fibers," "posted on the website" or "on the trail." Its negative side fires on "wall" in phrases like "stomach wall." Turning it up gave outputs that did not clearly relate to location.

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

    credit score, which the likes of ClearScore, Equifax and Call Credit allow you to do for free, and taking a few easy steps such as getting on the electoral register, you can

  2. #2 peak

    accessible to employees for all hazardous chemicals in their workplace. This may be done in many ways. For example, employers may keep the SDSs in a binder or on computers as long as the employees have immediate access to the information without leaving their work

  3. #3 peak

    our place in the solar system.⏎It took those roving teams months to assemble at designated points at the Arctic tip of Norway, in Canada's Hudson Bay and on a small island in the South Pacific. They battled the elements, disease, hunger

  4. #4 peak

    Control your speed⏎- Warn others when passing⏎- Keep dogs on a leash at all times for their protection, and for yours⏎- Respect all wildlife encountered on the trail<|endoftext|>In 1847, when Mormon pioneers arrived in the

  5. #5 peak

    opposites."⏎Opposites are everywhere in our world. A day at the park will reveal busy kids and active animals doing opposite actions. There, on the slide: Sam goes up as Hiroko zips down. And there,

  6. #6 peak

    school district has a list of bus rules and regulations posted on the district website to assist parents and staff in making sure students are safe. OSD

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 how I can use the power of the numbers to make the difference between the first and second and third digits, and the power of the numbers to make the difference between the first and second and third digits. So,

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

    and break food down into smaller particles using chemical and mechanical digestion.⏎The stomach can perform these roles due to the layers of the stomach wall. These are the gastric mucosa, submucosa, muscularis extern

  2. #2 peak

    stomach to distend upon the entry of the food. A bolus of food enters the stomach from the esophagus. The various tissue layers of the stomach wall then combine their functions to digest the bolus into a viscous, pulpy

  3. #3 peak

    you still find it daunting, why not brush up on your histology basics first?⏎- Stomach wall⏎- Muscularis externa⏎The stomach wall consists of 4 layers of tissue. From deep (external) to superficial (

  4. #4 peak

    War. Green safely ejected and was rescued from the Yellow Sea by an Air Rescue Service SA-16 Albatross flying boat.⏎Captain Fedorets closed on McConnell from

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. L4:1016 excites
  2. L4:3030 excites
  3. L7:2824 excites
  4. L1:1194 suppresses
  5. L5:3024 excites
  6. L4:1406 weakly excites
  7. L2:2307 weakly excites
  8. L7:1504 weakly suppresses
  9. L6:2392 weakly suppresses
  10. L5:3065 weakly excites
  11. L7:1383 weakly excites
  12. L5:1431 weakly excites
  13. L7:2655 weakly excites
  14. L7:1551 weakly suppresses
  15. L2:1226 weakly suppresses 'in' after belief verbs
  16. L4:2079 weakly suppresses
  17. L2:1798 weakly suppresses
  18. L7:2137 weakly excites
  19. L7:1780 weakly suppresses
  20. L7:2758 weakly suppresses
  21. L4:2109 weakly excites
  22. L7:1877 weakly excites
  23. L5:1644 weakly suppresses
  24. L1:2721 weakly suppresses

Feeds later layers

  1. L14:1122 strongly excites
  2. L18:749 excites
  3. L22:2554 excites
  4. L20:1905 excites
  5. L11:1187 excites
  6. L25:2569 excites
  7. L13:2135 excites
  8. L9:3031 suppresses
  9. L17:2101 excites
  10. L10:3068 excites
  11. L16:2852 excites 'in' after a noun or participle
  12. L12:2638 weakly excites
  13. L19:1345 weakly excites
  14. L12:2289 weakly excites 'of' after part-whole nouns
  15. L12:2833 weakly excites
  16. L14:1728 weakly excites "of" after a numbered section or title
  17. L17:2877 weakly excites
  18. L11:1369 weakly excites
  19. L19:252 weakly excites
  20. L18:2836 weakly suppresses
  21. L9:1025 weakly excites
  22. L19:649 weakly excites
  23. L12:2889 weakly excites
  24. L14:427 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 -1.86 and -1.701 values between -1.20 and -1.042 values between -0.87 and -0.7012 values between -0.70 and -0.5497 values between -0.54 and -0.37483 values between -0.37 and -0.211483 values between -0.21 and -0.041534 values between -0.04 and 0.12223 values between 0.12 and 0.2930 values between 0.29 and 0.459 values between 0.45 and 0.6210 values between 0.62 and 0.782 values between 0.78 and 0.954 values between 0.95 and 1.114 values between 1.11 and 1.283 values between 1.28 and 1.441 values between 1.44 and 1.613 values between 1.61 and 1.771 values between 2.10 and 2.271 values between 2.27 and 2.431 values between 3.43 and 3.591 values between 3.76 and 3.921 values between 4.58 and 4.75offnegativepositiveoften

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. ensively
  2. platforms
  3. isode
  4. 战场
  5. shelves
  6. naments
  7. реб
  8. ду
  9. ross
  10. riday

Suppresses

  1. pé
  2. 誉
  3. administr
  4. onian
  5. ế
  6. ónica
  7. onica
  8. xcf
  9. onyms
  10. amb