Neuron Explorer

Qwen3-0.6B

line break before a subheading

A neuron in layer 6 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 line break that comes right after a short bold-style subheading in web articles, such as "Lower your risk of heart disease". Turning it up did not give a clear, consistent change in the writing.

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

    highly conductive core. The supercapacitors are made of millions of nanometer-thick wires with two-dimensional material shells coating.⏎Reshaping mobile technology⏎The supercapacitors are also more durable. They don't degrade quickly over

  2. #2 peak

    people were the picture of health when they donated, later-in-life obesity, high blood pressure and diabetes can raise the risk of kidney disease.⏎Transplant surgery risks⏎"We're changing," says

  3. #3 peak

    dark loaves, brown rice and oatmeal, according to a Harvard study of nearly 43,000 men.⏎Lower your risk of heart disease⏎Eating

  4. #4 peak

    countries, including southern Zimbabwe, northern South Africa and eastern Botswana, which have already suffered heavy rains and mudslides.⏎Biodiversity and food security under threat⏎Mozambique’s National Institute for Disaster Management and Reduction states that about 1

  5. #5 peak

    feeding advocates insist that flavors in breast milk go beyond a simple enjoyment for the infant -- it might be important for health too.⏎Flavors Start in the Womb⏎"The fact that the flavor is passed to the<|endoftext|>Masdar City was a project

  6. #6 peak

    24 hours or longer. Late-onset asthma produces heavy inflammation of bronchial tubes and is the dominant cause of chronic asthma.⏎Differences in treatment⏎Discovering these two types of asthma reactions has caused doctors to modify their treatment plans

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 will not be going anywhere. I will be going to the city. So I will not go. But I will not buy a car, and I will not go on my own. And I will not be going to the city,

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

    the visit of the headman Yodhājīva to the Buddha. S.iv.308.<|endoftext|>The New International Encyclopædia/Kinkajou⏎|←Kinic acid||The New International Encyc

  2. #2 peak

    class at WSU.⏎What textbook is this problem found in?⏎Our data indicates that this problem or a close variation was asked in Chemistry: An Atoms First Approach - Zumdahl Atoms 1st 2nd Edition. You

  3. #3 peak

    web bug) has changed and needs re-indexing.⏎On the first release containing the indexer<|endoftext|>Publications and Tools⏎Comprehensive School Reform and Student Achievement: A Meta-Analysis -- This report is available from the Center for Research on the Education

  4. #4 peak

    essa Gray, Head of the Division for Least Developed Countries (LDCs), Small Island Developing States (SIDS) and Emergency Telecommunications for the International Telecommunication Union (ITU), argued that increasing

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. L5:2181 strongly suppresses
  2. L5:212 suppresses
  3. L3:371 suppresses
  4. L3:523 excites line break after a section heading
  5. L5:1034 excites
  6. L3:559 excites
  7. L3:373 suppresses
  8. L2:1706 excites
  9. L5:2313 weakly excites
  10. L0:1864 weakly excites
  11. L1:830 weakly suppresses
  12. L5:750 weakly excites
  13. L2:578 weakly excites
  14. L4:226 weakly suppresses
  15. L5:343 weakly excites
  16. L5:2468 weakly suppresses
  17. L4:1698 weakly suppresses
  18. L5:918 weakly excites
  19. L1:1518 weakly suppresses
  20. L4:887 weakly suppresses
  21. L4:864 weakly suppresses
  22. L5:1371 weakly excites
  23. L1:1069 weakly excites
  24. L1:496 weakly excites

Feeds later layers

  1. L9:257 excites
  2. L7:392 excites
  3. L10:1516 excites
  4. L10:1136 excites
  5. L11:1344 excites
  6. L7:1729 excites
  7. L8:1684 excites
  8. L10:494 excites
  9. L16:818 excites
  10. L10:963 excites
  11. L7:1356 excites
  12. L17:856 excites
  13. L11:1513 excites
  14. L10:471 suppresses
  15. L17:450 suppresses
  16. L7:2235 excites
  17. L24:1823 excites opening parenthesis before an acronym
  18. L17:689 excites
  19. L8:666 excites
  20. L11:729 weakly excites
  21. L9:351 weakly excites
  22. L12:2494 weakly excites
  23. L10:900 weakly excites
  24. L12:2261 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 -1.35 and -1.191 values between -1.19 and -1.0238 values between -0.68 and -0.51206 values between -0.51 and -0.34781 values between -0.34 and -0.171874 values between -0.17 and 0.00876 values between 0.00 and 0.1796 values between 0.17 and 0.3411 values between 0.34 and 0.513 values between 0.51 and 0.684 values between 0.68 and 0.857 values between 0.85 and 1.021 values between 1.02 and 1.193 values between 1.19 and 1.361 values between 1.70 and 1.861 values between 2.03 and 2.201 values between 4.74 and 4.911 values between 5.25 and 5.42offnegativepositiveoften

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. imoto
  2. odium
  3. ibase
  4. oid
  5. رون
  6. íst
  7. ؤ
  8. ọc
  9. icont
  10. оля

Suppresses

  1. ()});⏎
  2. ()]);⏎
  3. validationResult
  4. хран
  5. 豉
  6. oor
  7. atisfied
  8. .standard
  9. urret
  10. hears