Neuron Explorer

Qwen3-0.6B

word before 'type 2 diabetes' or a condition

A neuron in layer 7 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on the word just before a health condition or a category name, such as 'type' in 'type 2 diabetes' or 'family' in a taxonomy sentence. Turning it up made the model's writing drift into unrelated topics like history or philosophy, so the link to the steering text is weak.

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

    other colonial anthozoans and soft coral by their characteristic of incorporating sand and other small pieces of material into their tissue to help make their structure (except for the family Zoanthidae). A main characteristic of the order is that their tentacles

  2. #2 peak

    of Metabolic Syndrome X? Over time, normally years, the metabolic imbalances give rise to a greater risk of cardiovascular disease, heart disease, kidney failure, type 11 diabetes and so on. In fact, the cardiovascular coronary risk from

  3. #3 peak

    interested to know what to expect in the way of co-morbidities, including hypertension, impaired glucose tolerance (which leads to metabolic syndrome), heart disease, type 2 diabetes, and fatty liver disease, as well as less threatening conditions that

  4. #4 peak

    skin.⏎People, particularly men, with a specific form of the gene are both more likely to have lower percent body fat, but also to develop heart disease and type 2 diabetes. The gene seems to be associated having higher blood glucose and cholesterol

  5. #5 peak

    if learning with others can help enhance test scores.⏎There are numerous more contentious topics that might be used for great research paper issues. In case you’ve got a particular opinion about something, or about a problem that is of interest to you, it

  6. #6 peak

    move your body enough to get your heart rate up, you can start to have benefits. The mood enhancing effects of exercise can actually be used as a treatment for mild depression. And in addition, women who exercise more are also at a lower risk

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: a thing that can be measured and has a defined number of properties. Examples: A fruit: a whole, has a volume and a mass. Examples: A non-terminating decimal. Examples: A non-integer. Examples: A

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

    , Sea Level, Renewable Energy, Natural Resources, Climate, Weather, Non-Renewable Energy, Land, Conflict, Fire, Atmosphere, Food, Life &

  2. #2 peak

    are many reasons to switch to solar mobile power sources. The first reason is that solar energy is a renewable resource. This means that it will never run out and we can rely on it

  3. #3 peak

    . This information is vital for decision-making, financial analysis, and evaluating the company's ability to meet its financial obligations.⏎Assets represent what the company owns and include tangible items like cash, inventory, and property, as well as int

  4. #4 peak

    . The less people know about us the better.⏎2. The fewer people know about us the better.⏎In #1 "less" applies to an uncountable abstract, the implied knowledge.⏎In #2 "fewer" applies to the

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. L4:904 weakly excites
  2. L3:253 weakly excites
  3. L5:461 weakly excites
  4. L2:1133 weakly excites
  5. L5:771 weakly excites
  6. L1:2241 weakly excites
  7. L3:2731 weakly excites
  8. L2:473 weakly excites
  9. L3:1590 weakly suppresses
  10. L6:824 weakly excites
  11. L5:94 weakly suppresses
  12. L3:859 weakly excites
  13. L1:3070 weakly suppresses
  14. L1:2035 weakly suppresses
  15. L4:2409 weakly suppresses
  16. L6:263 weakly excites
  17. L1:1120 weakly suppresses 'for' after preparation or purpose nouns
  18. L5:8 weakly excites
  19. L0:2786 weakly suppresses
  20. L6:2109 weakly excites
  21. L6:7 weakly suppresses
  22. L6:1011 weakly excites
  23. L6:1135 weakly excites
  24. L4:379 weakly suppresses

Feeds later layers

  1. L9:1666 suppresses
  2. L9:2138 suppresses
  3. L13:2146 suppresses
  4. L8:391 suppresses
  5. L9:2714 suppresses
  6. L8:1135 suppresses
  7. L9:710 suppresses
  8. L9:1021 suppresses
  9. L9:663 suppresses
  10. L13:279 excites
  11. L8:946 suppresses
  12. L11:1385 suppresses
  13. L12:1273 suppresses
  14. L12:834 suppresses
  15. L15:260 weakly excites
  16. L10:1335 weakly suppresses
  17. L10:2456 weakly suppresses
  18. L16:2793 weakly suppresses
  19. L10:23 weakly suppresses
  20. L17:553 weakly suppresses
  21. L16:1819 weakly suppresses
  22. L9:2067 weakly suppresses
  23. L24:2777 weakly suppresses
  24. L20:1544 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 -3.07 and -2.951 values between -1.75 and -1.631 values between -1.63 and -1.512 values between -1.51 and -1.391 values between -1.39 and -1.272 values between -1.27 and -1.153 values between -1.15 and -1.032 values between -1.03 and -0.912 values between -0.91 and -0.7911 values between -0.79 and -0.677 values between -0.67 and -0.5515 values between -0.55 and -0.4332 values between -0.43 and -0.31127 values between -0.31 and -0.19566 values between -0.19 and -0.071759 values between -0.07 and 0.05957 values between 0.05 and 0.17298 values between 0.17 and 0.2978 values between 0.29 and 0.4121 values between 0.41 and 0.538 values between 0.53 and 0.653 values between 0.65 and 0.772 values between 0.77 and 0.894 values between 0.89 and 1.012 values between 1.01 and 1.132 values between 1.13 and 1.251 values between 1.61 and 1.73offnegativepositiveoften

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. BackingField
  2. plier
  3. spec
  4. intColor
  5. espec
  6. ting
  7. ыта
  8. 缓冲
  9. Facade
  10. RIA

Suppresses

  1. /non
  2. inear
  3. inite
  4. rous
  5. .non
  6. ечно
  7. 族自治州
  8. wrist
  9. OMET
  10. usive