Neuron Explorer

Qwen3-0.6B

word before a 'for' or 'with' object

A neuron in layer 13 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 the word right before a phrase that adds detail, such as 'dentist with', 'would know', 'study for', or 'has stories'. Turning it up made the model produce number-heavy math text, and turning it down made it lose its thread and write stuttering fragments.

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

    age 7, a child will have started to get adult molars in place, and the position of these and the primary teeth provide the child's general dentist with a good perspective of the development of

  2. #2 peak

    too small that no one can see, or making the text and background colours clash that make it impossible to read.⏎If you are typography nerd, then you would know something about the “Classic Scale”. This makes the readability of your PowerPoint smoother and

  3. #3 peak

    and Oxfam in Vietnam have collaborated on a research report on the effects of disasters and climate change on multidimensional inequality in Vietnam. Please check the complete study for more information on the data and analysis.<|endoftext|>Parus niger (Southern black

  4. #4 peak

    I never did find out what was the matter. Maybe a deer? This is just one example of a horse spooking. Anyone who has been around horses has stories of horses spooking, sometimes for no reason at all.⏎Quick Re

  5. #5 peak

    down in the photo, is carved and ground into an unmistakable human female form, while the back remains mostly⏎unworked gray cortex. In the photos above note the clear morphological similarity of the figure to that of the well known Neolithic

  6. #6 peak

    the types of broken bones, including:⏎TransverseA bone break is considered transverse when the fracture extends across the bone.⏎SpiralAs you may have guessed, a spiral fracture spirals around the bone.⏎ObliqueAn oblique fracture

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 point that, when we are in the space of the points that are on the surface of the space that are defined by the set of points that are the points on the curve in the space space that are the curve on the curve in

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

    loose with our terms, but that just makes it more confusing.⏎You ought to be able to think these through - take a shot and we'll tell you where you're on and off-target.⏎Ok, thats a good idea.⏎1. Unfortunately

  2. #2 peak

    natural predators. These predators include other insects and parasites. Insects that feed on whiteflies include the lady beetle and lacewings. Parasites that use whiteflies as a host species are the tiny wasps in the Encarsia genus.

  3. #3 peak

    both Greek and English, offers the visitor a fascinating tour in a simple and understandable way, utilizing modern audiovisual media. Even small fragments which seem insignificant at first glance, create an opportunity to reconstruct the facts,

  4. #4 peak

    of Lagos. She has been trying to get a loan to support her maize business to no avail; a number of microfinance banks that Akande approached declined to give her a loan. Among the challenges she also faces is the high price of fertil

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. L11:361 suppresses
  2. L12:2279 suppresses
  3. L9:2390 suppresses
  4. L12:969 suppresses
  5. L9:1322 excites unclear: medical symptom lists and materials
  6. L12:328 excites
  7. L12:372 suppresses
  8. L4:463 excites
  9. L11:1327 excites
  10. L8:408 excites
  11. L12:2145 excites
  12. L12:2899 weakly excites
  13. L11:579 weakly suppresses
  14. L11:294 weakly excites
  15. L12:2722 weakly excites
  16. L9:361 weakly excites
  17. L10:616 weakly excites
  18. L12:1207 weakly suppresses
  19. L6:1231 weakly suppresses
  20. L5:2236 weakly excites
  21. L11:708 weakly suppresses
  22. L1:753 weakly suppresses
  23. L12:1065 weakly suppresses
  24. L9:341 weakly excites

Feeds later layers

  1. L14:1060 excites
  2. L15:576 excites
  3. L14:778 excites
  4. L15:1943 suppresses
  5. L16:749 excites
  6. L19:2665 excites
  7. L16:1768 excites
  8. L14:551 excites
  9. L15:1513 weakly excites
  10. L15:1569 weakly excites
  11. L14:252 weakly excites
  12. L14:1124 weakly excites
  13. L14:453 weakly excites
  14. L17:2515 weakly excites
  15. L14:674 weakly excites
  16. L14:1252 weakly suppresses
  17. L16:98 weakly suppresses
  18. L16:1315 weakly excites word or phrase being named or defined
  19. L15:448 weakly suppresses
  20. L15:182 weakly excites
  21. L16:304 weakly excites
  22. L14:2042 weakly excites comma after 'For X,' introducing a viewpoint
  23. L14:2669 weakly excites
  24. L15:360 weakly excites

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 -2.61 and -2.472 values between -2.06 and -1.931 values between -1.93 and -1.792 values between -1.79 and -1.653 values between -1.65 and -1.511 values between -1.51 and -1.384 values between -1.38 and -1.246 values between -1.24 and -1.1013 values between -1.10 and -0.9719 values between -0.97 and -0.8340 values between -0.83 and -0.6988 values between -0.69 and -0.55152 values between -0.55 and -0.42254 values between -0.42 and -0.28444 values between -0.28 and -0.141054 values between -0.14 and -0.001193 values between -0.00 and 0.13297 values between 0.13 and 0.27124 values between 0.27 and 0.4173 values between 0.41 and 0.5442 values between 0.54 and 0.6828 values between 0.68 and 0.8218 values between 0.82 and 0.9613 values between 0.96 and 1.099 values between 1.09 and 1.235 values between 1.23 and 1.379 values between 1.37 and 1.513 values between 1.51 and 1.642 values between 1.64 and 1.782 values between 1.78 and 1.921 values between 1.92 and 2.052 values between 2.05 and 2.191 values between 2.33 and 2.471 values between 2.60 and 2.741 values between 2.74 and 2.88offnegativepositiveoften

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. xn
  2. fully
  3. culture
  4. /off
  5. 内的
  6. führer
  7. _average
  8. _or
  9. umble
  10. խ

Suppresses

  1. 】【
  2. 年后
  3. getResult
  4. getTable
  5. نز
  6. 棵树
  7. 蛎
  8. setResult
  9. redi
  10. estone