Neuron Explorer

Qwen3-0.6B

"how do you" question phrase

A neuron in layer 0 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 "you" right after "how do" in questions, such as "How do you outline notes?" Turning it up made the model write questions and prompts, which fits the trigger.

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

    headings.⏎How do you outline notes?⏎drawn, the outline method should be replaced with a better note

  2. #2 peak

    use the networks for communication purposes. In education, we have online libraries that we can visit on our home PC. All of this is<|endoftext|>Describe a how do you cite a research paper time when you had to solve a problem without classification essay writing

  3. #3 peak

    imagination in motion.⏎How do you send your child to NERF Camp?⏎All you have to do is to

  4. #4 peak

    's disease, and how do you differentiate between regular memory loss and memory loss associated with Alzheimer's disease?⏎Answer:

  5. #5 peak

    an edited transcript.⏎Mainebiz: How do you think increasing commercial demand for forest products will affect Maine's forests?⏎Barton:

  6. #6 peak

    polymorphisms that can be analyzed in a human nuclear background, and provide a novel model for the study of nuclear-mitochondrial interactions.<|endoftext|>How do you learn best?⏎In a recent post, I mentioned the concept of learning styles.

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 have been thinking about how to use the information to make a question for you to answer. So, for example, if you are thinking about how to use the information to make a question for me to answer, then I can say:

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

    thraquinone, which has a natural chemical attraction<|endoftext|>From: Michael Barrie <mibarrieinterchange.ubc.ca>⏎Subject: Overt Markers on Mass Nouns⏎E-mail this message to a friend⏎Query

  2. #2 peak

    differing modes of inheritance. Agreement appears to be near at hand that IDDM and NIDDM exhibit substantial genetic differences.⏎Stages of Diabetes⏎1. Overt or manifest diabetes⏎It refers to the fully expressed clinical syndrome. This stage of

  3. #3 peak

    Columbus⏎The long low ship, With a high stern and pierced for many oars, glides effortlessly up the long narrow bay under its towering square sail.⏎After

  4. #4 peak

    days, replenishing the ship with food, water, precious exotic hides, and many other things, the got underway hours before the morning breeze. Their many oars glided their craft like a ghostly apparition southward down the bay toward

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

None: this is the first layer.

Feeds later layers

  1. L8:474 weakly excites
  2. L23:1016 weakly excites
  3. L25:3016 weakly excites
  4. L7:1409 weakly excites
  5. L14:1255 weakly suppresses
  6. L11:825 weakly suppresses
  7. L3:3038 weakly suppresses
  8. L3:1879 weakly suppresses
  9. L16:2696 weakly excites
  10. L12:2204 weakly excites
  11. L23:1444 weakly suppresses
  12. L17:741 weakly excites
  13. L1:1979 weakly excites
  14. L5:2315 weakly excites
  15. L11:2223 weakly excites
  16. L22:1105 weakly excites
  17. L19:1095 weakly suppresses
  18. L4:595 weakly suppresses
  19. L7:73 weakly suppresses
  20. L15:2469 weakly excites
  21. L15:1507 weakly suppresses
  22. L2:3034 weakly suppresses
  23. L20:1017 weakly suppresses
  24. L13:1622 weakly 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.

1 values between -0.62 and -0.5212 values between -0.32 and -0.22100 values between -0.22 and -0.121033 values between -0.12 and -0.022437 values between -0.02 and 0.08302 values between 0.08 and 0.1817 values between 0.18 and 0.282 values between 0.28 and 0.381 values between 0.38 and 0.471 values between 0.57 and 0.671 values between 1.66 and 1.761 values between 3.25 and 3.35offnegativepositiveoften

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. щен
  2. roid
  3. roids
  4. enaries
  5. hood
  6. loid
  7. hud
  8. 肌
  9. handled
  10. ryo

Suppresses

  1. DataTypes
  2. ')[
  3. 罢了
  4. 的人来说
  5. imate
  6. 邻居
  7. ':⏎⏎
  8. 这样说
  9. 靛
  10. ")[