Neuron Explorer

Qwen3-0.6B

"and" joining questions (wh-question context)

A neuron in layer 17 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 fires on the word "and" when it follows a question, joining it to a second question as in "Where will that money come from, and why...". It works in the opposite direction on words like "who" and "what" inside embedded questions. Turning it up made the model repeat the word "what" over and over, which fits its link to question words.

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

    guides, fun facts, and photography you find here will inspire you to explore new places!<|endoftext|>Will there be radiation when the mobile phone signal is shielded, and is it harmful to the human body?⏎Regarding radiation, as long as electronic products

  2. #2 peak

    County, there is now a new birth and a new way to remember a rich history .⏎What happened to the hamlet of Huntertown in Woodford County, and

  3. #3 peak

    have recently been revised. We explore their history and increase in popularity.<|endoftext|>Native Plants for the Mid-Atlantic⏎On this page⏎- What Are Native Plants and Why Are They Important?⏎- State-Specific Native Plant Organizations⏎- Other Sources

  4. #4 peak

    mineral or non-mineral based oils) or a synthetic blend (or hydrocarbon-based oils and synthetic-based oils).⏎But which motor oil is best for your vehicle and what’s the difference between all the different types, weights and other options

  5. #5 peak

    worlds around other stars has shown that planets orbit at least 5 to 10 percent of all stars. But how many of these planets are Earth-size, and possibly Earth-like?<|endoftext|>& Tornado Alley⏎Jan Mikusinski developed an

  6. #6 peak

    Fred Gibbs and I were awarded from Google to mine their vast collection of books.]⏎Why did the Victorians look to mathematics to achieve certainty, and how we might understand the Victorians better with the mathematical methods they bequeathed

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 see, and I can know, and I can know more? And I can know more, and I can know more, and I can know more? The more I know, the more I can know? This is a part

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

    %. In order to achieve this objective the marketer has to prepare a plan in respect of the level of production and promotion efforts. It will also be decided as to who will do what, when and how. To do this is known as marketing planning

  2. #2 peak

    needed. While it may sound trivial, the decision on what to produce/grow has important ramifications. If you plan to grow/produce a

  3. #3 peak

    battery. This article will be broken into two parts, the "How-to" and the "Why." The How-to section features detailed instructions with illustrations, including what tools you'll need, how to wire connections, and other important safety tips.

  4. #4 peak

    at home. Here are some simple tips that you can make your garden look more beautiful.⏎According to expert, before making a garden, first you have to consider what is the concept of the building of your home. After that, adjust your garden

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. L15:1473 strongly excites
  2. L11:296 suppresses
  3. L4:470 suppresses
  4. L4:927 excites
  5. L9:75 excites 'what' or 'how' after see or understand
  6. L8:1997 excites
  7. L16:2975 suppresses
  8. L4:2558 excites
  9. L12:1667 excites
  10. L5:2657 suppresses
  11. L9:524 excites
  12. L5:458 excites
  13. L13:344 suppresses
  14. L5:1800 weakly suppresses
  15. L7:1081 weakly suppresses
  16. L13:2728 weakly suppresses
  17. L1:2951 weakly suppresses
  18. L2:1640 weakly excites
  19. L0:1878 weakly suppresses
  20. L16:817 weakly suppresses
  21. L6:687 weakly excites
  22. L0:1966 weakly suppresses
  23. L5:702 weakly suppresses
  24. L10:722 weakly excites

Feeds later layers

  1. L21:728 strongly excites
  2. L18:2517 excites
  3. L23:594 excites
  4. L27:656 excites
  5. L19:2643 excites "is" in "what is" questions
  6. L19:2814 excites
  7. L18:2031 suppresses
  8. L25:576 excites
  9. L20:1371 suppresses comma inside a question
  10. L22:543 excites
  11. L18:1586 excites
  12. L25:541 suppresses
  13. L26:1046 excites
  14. L19:1703 suppresses
  15. L24:1439 excites
  16. L27:233 suppresses
  17. L22:1933 excites
  18. L26:400 excites
  19. L19:1514 weakly excites
  20. L22:1414 weakly excites
  21. L26:1836 weakly excites
  22. L23:1089 weakly excites
  23. L26:1104 weakly excites
  24. L18:1918 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.

3 values between -32.06 and -31.052 values between -28.02 and -27.001 values between -23.97 and -22.962 values between -22.96 and -21.942 values between -20.93 and -19.922 values between -19.92 and -18.912 values between -18.91 and -17.902 values between -17.90 and -16.881 values between -15.87 and -14.862 values between -14.86 and -13.851 values between -11.82 and -10.813 values between -10.81 and -9.801 values between -8.79 and -7.783 values between -6.77 and -5.755 values between -5.75 and -4.746 values between -4.74 and -3.7310 values between -3.73 and -2.7212 values between -2.72 and -1.7118 values between -1.71 and -0.692976 values between -0.69 and 0.32849 values between 0.32 and 1.331 values between 1.33 and 2.341 values between 2.34 and 3.351 values between 3.35 and 4.371 values between 4.37 and 5.381 values between 7.40 and 8.41offnegativepositiveoften

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. 为何
  2. 如何
  3. 为什么
  4. why
  5. how
  6. 多么
  7. 何时
  8. 什么原因
  9. 什么意思
  10. 有多少

Suppresses

  1. ?
  2. ?\
  3. 呢
  4. ? ⏎
  5. ?
  6. ?⏎
  7. ?p
  8. ?⏎⏎
  9. ?,
  10. ef