Neuron Explorer

Qwen3-0.6B

"D" in vitamin D and version digits

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

Fires mostly on the letter D in "vitamin D", and also on digits in version numbers such as "Ubuntu 22.04" or "OS X 10.1". The steering results do not show a theme linked to vitamins, so the effect on writing is unclear.

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

    computer, this engaging CD makes learning the parts of speech fun and challenging for the entire class.⏎PC: Windows XP and up⏎Mac: OS X (10.1) and up⏎Resolution: 800 x 60

  2. #2 peak

    unzipping the .tgz files using the terminal. Let’s get into these.⏎Note: For this particular tutorial, we will use the Ubuntu 22.04. However, the commands used here are same for all the distributions

  3. #3 peak

    even 10% may be too much of a weekly mileage increase for some runners.⏎The causes of low bone density include genetics, poor dietary calcium or vitamin D intake, and a history of menstrual disorders, meaning a gap of six months or

  4. #4 peak

    working with resistanec bands or weights.⏎Diet: Calcium and Vitamin D are important for strong bones. High-calcium foods include:⏎- Dairy products

  5. #5 peak

    10.3390/nu8020068⏎- Calcium/Vitamin D Requirements, Recommended Foods & Supplements.” National Osteoporosis Foundation, https://

  6. #6 peak

    ake?⏎The amount of research about vitamin D and its relation to mood swings and depression is growing.⏎In addition to its well-known role in calcium absorption, vitamin D activates genes that regulate the immune system and release neurotransmitters (e.g., dopamine

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 not a mathematician. (A) the number of my math... something / something / the number of my math... something / something / the number of my math... something / something / the number of my math... something /

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 the Piemonte-Toscana region of northern/central Italy (images only, February-March, 2009).⏎In Fort Yukon, Alaska, salmon is a mainstay of the diet. Yet, among the

  2. #2 peak

    nowhere to lay His head."⏎King James BibleAnd Jesus said unto him, Foxes have holes, and birds of the air [have] nests; but the Son of man hath not where to lay [his] head.⏎Parallel VersesInternational

  3. #3 peak

    is a remote and relatively undeveloped region in the Yukon that spans an area of 67,431 square kilometres. The Government of Yukon (“Yukon”) manages 97.3% of the Watershed

  4. #4 peak

    Jesus, but we need to consider why the Father sent His Son. God performed a miracle (the Incarnation) not as an end to itself

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. L5:2552 weakly excites
  2. L7:57 weakly excites
  3. L7:1683 weakly suppresses
  4. L3:533 weakly excites
  5. L3:2335 weakly excites
  6. L7:954 weakly excites
  7. L7:1912 weakly excites
  8. L6:2583 weakly excites
  9. L3:707 weakly suppresses
  10. L1:924 weakly suppresses
  11. L2:1895 weakly suppresses
  12. L7:985 weakly excites
  13. L5:832 weakly excites
  14. L1:1103 weakly suppresses
  15. L1:1119 weakly suppresses
  16. L5:2587 weakly suppresses
  17. L5:2800 weakly suppresses
  18. L5:1426 weakly excites
  19. L6:797 weakly suppresses
  20. L2:1710 weakly suppresses
  21. L7:1873 weakly suppresses
  22. L5:1597 weakly excites
  23. L0:1413 weakly suppresses
  24. L2:2095 weakly suppresses

Feeds later layers

  1. L9:716 excites
  2. L10:952 suppresses
  3. L9:1026 excites
  4. L15:646 excites
  5. L13:1001 suppresses
  6. L10:1316 excites
  7. L10:2105 excites
  8. L11:122 suppresses
  9. L13:1513 excites
  10. L12:576 excites 'of' in fixed phrases like table of contents
  11. L9:1298 suppresses
  12. L13:450 suppresses
  13. L9:116 excites
  14. L9:845 excites
  15. L14:2288 excites
  16. L10:1705 excites
  17. L10:129 suppresses
  18. L11:393 excites
  19. L15:1299 suppresses
  20. L12:887 excites
  21. L9:401 excites
  22. L11:966 suppresses
  23. L13:2328 suppresses
  24. L17:870 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 -1.43 and -1.371 values between -0.69 and -0.633 values between -0.63 and -0.574 values between -0.57 and -0.5110 values between -0.51 and -0.4512 values between -0.45 and -0.3924 values between -0.39 and -0.3336 values between -0.33 and -0.2788 values between -0.27 and -0.21184 values between -0.21 and -0.15389 values between -0.15 and -0.08753 values between -0.08 and -0.021125 values between -0.02 and 0.04646 values between 0.04 and 0.10334 values between 0.10 and 0.16168 values between 0.16 and 0.2272 values between 0.22 and 0.2835 values between 0.28 and 0.3414 values between 0.34 and 0.414 values between 0.41 and 0.471 values between 0.47 and 0.533 values between 0.53 and 0.591 values between 0.96 and 1.02offnegativepositiveoften

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. 且
  2. rib
  3. 檔案
  4. ,),⏎
  5. bery
  6. uhan
  7. tienes
  8. 一封信
  9. Ệ
  10. 点

Suppresses

  1. bidden
  2. ertainment
  3. imony
  4. 骝
  5. article
  6. ourt
  7. ewise
  8. -fashioned
  9. imageSize
  10. anness