Neuron Explorer

Qwen3-0.6B

the word 'course' in course blurbs

A neuron in layer 11 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 reacts to the word "course" when it refers to a class or online course, such as "In this course" or "Before attending this course". Turning it up gave text about learning and training, but the links are loose.

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

    016.⏎These media resources form part of an on-demand Coursera MOOC run by Frank Cogliano; Professor of American History,

  2. #2 peak

    including the date of preparation or last revision. The SDS must also state that no applicable information was found when the preparer does not find relevant information<|endoftext|>About This Course⏎Learn the fundamentals of Spark, the technology that is revolutionizing the analytics and

  3. #3 peak

    lessons⏎- Available on completion⏎- Course author⏎- Programming Tut⏎- They will have an excellent understanding of the fundamentals in Java programming.⏎- In this course you will get a head-start into your Java studies⏎- In this course you

  4. #4 peak

    ⏎Who should attendExperienced programmers who need to learn the syntax and functionality of the SAS LASR Analytic Server and the IMSTAT procedure⏎Before attending this course, you should have experience writing SAS programs or working with other languages such as R

  5. #5 peak

    elt, rainfall frequency, and the hydrologic cycle. The streamflow estimation procedures presented are the rational method and the unit hydrograph.⏎Upon successful completion of this course, the student will be able to:⏎CIVL 1060

  6. #6 peak

    NSM2012. You'll have 30 days to complete the course.⏎For the younger driver, the North Dakota Safety Council is also introducing Defensive Driving

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 don't know what I have." "I don't know what I have." I don't know what I have." "Let me have it, let me have it, let me have it, let me have it." "

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

    And by doing group project work and presentations, they could inform other classmates and teachers (i.e., project-based and cooperative learning).

  2. #2 peak

    arts related fields, but in other academic areas as well.⏎Arts education develops students who are self driven and motivated as they are often the toughest critics of their own

  3. #3 peak

    , they help children explore the outdoors while developing learning skills.⏎- Getting your Bearings⏎- How Artistic are you?⏎-

  4. #4 peak

    sharing playing time, and respecting rules. They understand that rules are important for everyone, and that without regulations, games would become unfair.⏎Although competition helps children develop problem solving and other skills, it can be both positive and negative. Negative competition

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. L9:1741 excites
  2. L10:863 suppresses
  3. L9:2657 suppresses
  4. L6:2984 suppresses
  5. L8:2772 suppresses
  6. L10:2796 excites
  7. L6:2991 suppresses
  8. L6:1250 excites
  9. L9:1018 excites
  10. L3:469 weakly suppresses
  11. L9:395 weakly suppresses
  12. L7:2603 weakly excites
  13. L10:1834 weakly excites
  14. L10:893 weakly excites
  15. L8:2155 weakly excites
  16. L10:2519 weakly suppresses
  17. L9:1681 weakly suppresses
  18. L10:1690 weakly excites
  19. L5:354 weakly excites
  20. L10:2352 weakly excites
  21. L9:2977 weakly excites
  22. L3:1155 weakly excites
  23. L6:1686 weakly excites
  24. L6:2814 weakly excites

Feeds later layers

  1. L20:918 excites
  2. L25:1540 excites
  3. L18:2533 excites
  4. L17:792 excites
  5. L18:2249 excites
  6. L21:1958 excites
  7. L20:2884 excites
  8. L21:1666 excites
  9. L21:2422 excites
  10. L21:3035 excites
  11. L26:387 excites
  12. L21:1608 excites
  13. L21:2739 excites
  14. L16:1857 excites
  15. L19:1035 excites
  16. L18:3054 excites
  17. L26:382 excites
  18. L18:2104 excites
  19. L25:641 excites
  20. L19:1897 excites
  21. L19:2246 excites
  22. L26:909 excites
  23. L21:2991 excites
  24. L19:2399 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 -2.18 and -1.971 values between -1.54 and -1.334 values between -1.33 and -1.124 values between -1.12 and -0.9110 values between -0.91 and -0.7014 values between -0.70 and -0.49113 values between -0.49 and -0.281074 values between -0.28 and -0.062312 values between -0.06 and 0.15280 values between 0.15 and 0.3645 values between 0.36 and 0.577 values between 0.57 and 0.7814 values between 0.78 and 0.992 values between 0.99 and 1.2012 values between 1.20 and 1.425 values between 1.42 and 1.633 values between 1.84 and 2.053 values between 2.47 and 2.681 values between 2.68 and 2.901 values between 2.90 and 3.111 values between 3.95 and 4.161 values between 6.07 and 6.28offnegativepositiveoften

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. training
  2. training
  3. .training
  4. tutorials
  5. (training
  6. 教育培训
  7. 学员
  8. tutorial
  9. -training
  10. 教程

Suppresses

  1. anch
  2. urd
  3. ira
  4. oper
  5. 甾
  6. obody
  7. arta
  8. 数据
  9. odash
  10. urn