Neuron Explorer

Qwen3-0.6B

dash starting a new list item

A neuron in layer 7 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 responds to the dash or bullet mark that begins a new item in a list, especially a list of questions or points. Turning it up pushed the text toward more questions and quiz-style lines.

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

    corium (dermal soft tissue); third phalanx (bone P3)⏎How quickly does sole and wall grow, and what is the normal length?⏎- sole: 4mm/month⏎- wall: 5-6mm/month

  2. #2 peak

    10 commandments from God?⏎- What are we told to do in the fifth commandment?⏎HONOR OUR FATHER AND OUR MOTHER⏎- What was the name of Moses' brother?⏎

  3. #3 peak

    bad? Why?⏎- How did the children feel when the giant told them to leave?⏎Watch the video and then talk about the discussion points with an adult.⏎o Who did Tia want to<|endoftext|>| Quote #1⏎Richard's first mention

  4. #4 peak

    This prophet was swallowed by a fish.⏎- What animal was often used for transportation in the Bible?⏎CAMEL or DONKEY (either answer is correct)⏎- Who was the Son of God?⏎- What was the name of Jesus' mother

  5. #5 peak

    Balance Sheet (Assets, Liabilities & Equity)⏎• Understanding Cash Flows (Operating, Investing & Financing)⏎Analysing & Interpreting Financial Statements⏎• Understanding Vertical Analysis⏎• Understanding Ratios (Performance, Liquidity & Leverage

  6. #6 peak

    daily basis.⏎- Countries from Africa, Asia-Pacific and the European Union too have expressed their support for the Bali Declaration.⏎About Minamata Convention on Mercury⏎- The Minamata Convention on Mercury is the most recent global agreement on environment and

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 can't. I'm just a number. I am a number. I don't know. I don't know. So, I can't. I can't. So, I can't. I can’t. I can't

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

    results demonstrate that silkworm-BEVS is a promising alternative strategy to produce the functional and thermostable reverse transcriptase.⏎All Science Journal Classification (ASJC) codes⏎- Insect Science<|endoftext|>An account of the religion of

  2. #2 peak

    0,10 250,190 160,210" style="fill:lime;stroke:yellow;stroke-width:1"/> </svg>⏎Here is what the above code looks like in HTML

  3. #3 peak

    -layer coated, triple-layer coated and graded-index-layer coated samples was performed and compared with experimentally derived films. Good agreement between model and experiment was observed.⏎ASJC Scopus subject areas⏎- Electronic, Optical and Magnetic Materials⏎- Ceramics

  4. #4 peak

    diverse set of controls, as well as in a discontinuity analysis on observations near the borders between anglophone and francophone countries.⏎- Colonial rule⏎ASJC Scopus subject areas⏎- Economics and Econometrics⏎- Organizational Behavior and

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. L6:164 suppresses
  2. L5:329 excites dash starting a new list item
  3. L4:453 excites
  4. L6:606 suppresses
  5. L5:103 weakly suppresses
  6. L5:89 weakly suppresses
  7. L6:172 weakly suppresses
  8. L2:209 weakly excites 'also' after 'not only ... but'
  9. L4:1074 weakly excites
  10. L5:877 weakly excites
  11. L4:25 weakly excites
  12. L0:1163 weakly excites
  13. L4:15 weakly suppresses
  14. L2:2112 weakly suppresses
  15. L4:139 weakly suppresses
  16. L4:19 weakly suppresses
  17. L6:13 weakly excites
  18. L2:111 weakly suppresses
  19. L5:775 weakly suppresses
  20. L4:97 weakly suppresses
  21. L4:288 weakly suppresses
  22. L2:375 weakly suppresses
  23. L5:2904 weakly suppresses
  24. L6:1113 weakly excites

Feeds later layers

  1. L10:1676 weakly excites
  2. L8:1226 weakly excites
  3. L12:1544 weakly excites
  4. L11:729 weakly excites
  5. L8:1036 weakly excites
  6. L8:2812 weakly excites
  7. L17:1854 weakly excites
  8. L8:186 weakly suppresses
  9. L13:2437 weakly excites
  10. L19:1757 weakly excites
  11. L26:1888 weakly suppresses
  12. L21:2948 weakly excites
  13. L10:681 weakly suppresses
  14. L13:371 weakly excites
  15. L15:2450 weakly excites
  16. L22:90 weakly suppresses
  17. L17:806 weakly excites
  18. L14:1946 weakly excites
  19. L9:229 weakly excites
  20. L10:332 weakly excites
  21. L25:1694 weakly suppresses 'and' joining paired names or fields
  22. L24:2550 weakly excites
  23. L11:1022 weakly excites
  24. L15:1050 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 -2.12 and -1.961 values between -1.00 and -0.841 values between -0.84 and -0.687 values between -0.68 and -0.5219 values between -0.52 and -0.36178 values between -0.36 and -0.201383 values between -0.20 and -0.041873 values between -0.04 and 0.13394 values between 0.13 and 0.2948 values between 0.29 and 0.452 values between 0.45 and 0.611 values between 4.14 and 4.30offnegativepositiveoften

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. Cove
  2. amarin
  3. cribed
  4. adelphia
  5. riad
  6. hait
  7. itate
  8. すでに
  9. case
  10. licity

Suppresses

  1. *</
  2. goog
  3. ollo
  4. 火烧
  5. nehmen
  6. burnt
  7. entlich
  8. ーン
  9. ulg
  10. *</