Neuron Explorer

Qwen3-0.6B

art, paintings and painters

A neuron in layer 6 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 about art, such as 'sampling', 'urban' in a painting context, and 'character' in illustration. It goes strongly negative on the names of painters like Monet and Van Gogh. Turned up, the model's writing kept repeating numbers and temperatures rather than art.

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

    2007. The result is encouraging. The model provides an objective basis for the development of acid rain forecasting operation in the province.⏎This is a preview of subscription content

  2. #2 peak

    is anchored in time and history, but it also provides a broad tour of music from the global movement against the brutal Apartheid regime. We’ve collected a sampling of songs from traditional South African folk songs, and protest songs from famous musicians from

  3. #3 peak

    or a favorite teacher.⏎- Think of famous people and take turns introducing them.⏎Copyright © 2004 by Susan Kettmann. Excerpted from The 2,000 Best Games & Activities with permission of its publisher

  4. #4 peak

    paintings were of peasant life in sombre colours. Once settled in Paris, however, his paintings took on new painting styles and brighter colours, and he started painting urban and suburban subjects. He liked the bright colours Impressionists used, and left

  5. #5 peak

    period (1603-1868). It is a form of woodblock printing that was popular among the common people of Japan, depicting scenes from everyday life, landscapes, and popular culture. Ukiyo-e prints were affordable

  6. #6 peak

    own characters first? You will get better faster if you! This article will go over some basic steps to get you started with digital character illustration.⏎Tips for digital character<|endoftext|>A city of ancient Sumer in southern Mesopotamia on a site

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 pieces are a mix of watercolor and oil paintings, and I am currently working on the final work. The painting is titled "The Last Days of a Painted Figure". I have been painting this work in my own words for the

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

    Charles Gleyre (1806 – 1874) (Gleyre Marc-Gabriel trained students such as Renoir, Monet, Sisley), he attended from 1875 training in the

  2. #2 peak

    - blue paper⏎- black paper⏎- pencil top eraser⏎The piece we selected to recreate was Van Gogh’s Starry Night. We’ve been learning about apples this week, an easy

  3. #3 peak

    to various mediums of art and famous artists and pieces of art. This week we did a quick lesson using this adorable book called Touch the Art: Make Van Gogh’s Bed by Julie Appel and Amy Guglielmo.⏎Touch the

  4. #4 peak

    steps go through blank cells or even part of an entirely different shape.⏎In a stroke of genius, Leo realised that the most important aspect of a post-cubist squarist painting is the largest diameter of any shape. He announces that there

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. L4:807 suppresses
  2. L3:993 suppresses
  3. L4:1264 excites
  4. L4:1727 suppresses
  5. L5:198 excites unclear: weak "and" in lists
  6. L5:62 excites
  7. L4:2220 weakly suppresses
  8. L5:94 weakly suppresses
  9. L3:691 weakly excites
  10. L4:2541 weakly excites
  11. L3:122 weakly excites
  12. L2:1657 weakly excites
  13. L5:84 weakly suppresses
  14. L1:1464 weakly excites
  15. L5:2922 weakly excites
  16. L4:1252 weakly excites
  17. L5:1818 weakly suppresses
  18. L5:293 weakly excites
  19. L4:2680 weakly suppresses
  20. L1:2801 weakly excites
  21. L1:331 weakly suppresses
  22. L3:464 weakly excites
  23. L5:132 weakly suppresses
  24. L0:1 weakly suppresses

Feeds later layers

  1. L23:2973 suppresses
  2. L10:2348 suppresses
  3. L20:2649 suppresses
  4. L7:1801 suppresses
  5. L9:1925 suppresses
  6. L20:2050 suppresses
  7. L21:2123 suppresses
  8. L7:2298 suppresses
  9. L21:1229 suppresses
  10. L25:1584 suppresses art and artist names in lists
  11. L23:1523 suppresses
  12. L24:1561 suppresses
  13. L20:2537 suppresses
  14. L26:360 suppresses
  15. L24:1754 suppresses
  16. L20:1990 suppresses
  17. L26:3031 suppresses
  18. L8:2369 suppresses
  19. L20:319 excites
  20. L24:2646 suppresses
  21. L27:1279 suppresses
  22. L9:907 suppresses
  23. L10:505 suppresses
  24. L26:1739 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 -5.17 and -5.011 values between -4.54 and -4.381 values between -2.80 and -2.641 values between -2.48 and -2.321 values between -2.32 and -2.171 values between -1.85 and -1.693 values between -1.69 and -1.531 values between -1.53 and -1.373 values between -1.37 and -1.224 values between -1.22 and -1.063 values between -1.06 and -0.903 values between -0.90 and -0.744 values between -0.74 and -0.5811 values between -0.58 and -0.4332 values between -0.43 and -0.27245 values between -0.27 and -0.111651 values between -0.11 and 0.051495 values between 0.05 and 0.21377 values between 0.21 and 0.3765 values between 0.37 and 0.523 values between 0.52 and 0.681 values between 1.00 and 1.16offnegativepositiveoften

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. ellan
  2. ivia
  3. uada
  4. icana
  5. swick
  6. ickers
  7. Crunch
  8. Kimber
  9. igration
  10. ellers

Suppresses

  1. paints
  2. paintings
  3. 艺术品
  4. painting
  5. paint
  6. 艺术家
  7. artistic
  8. artists
  9. artworks
  10. 作品