Neuron Explorer

Qwen3-0.6B

"how" after "learn" or "demonstrate"

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 word "how" after phrases like "you will learn how" or "demonstrate how", where a how-to explanation is about to follow. Turning it up or down did not produce a clearly related change in the written text.

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

    and clear. Deciding upon the structure of a report can often be one of the most challenging tasks, particularly for un<|endoftext|>In this tutorial, you will learn how to illustrate a bee icon using simple shapes and colors. This adorable insect can be

  2. #2 peak

    textbook will demonstrate how an answer is reached. Students can use the textbook to find answers and explanations.

  3. #3 peak

    majority of cancers, may involve an interplay between specific environmental factors related to epigenetic regulation of the genetic blueprint. Epigenetics provides a compelling model for how environmental influences throughout development can have life-long (and potentially multi-generational)

  4. #4 peak

    inders where the child must find the matching sound pairs by listening and then grade the boxes from the loudest to the soft<|endoftext|>In this tutorial, you will learn how to animate a bouncing ball lazily and really quickly!⏎If you plan to become

  5. #5 peak

    at innovative mathematics.⏎Numbers worksheets enable you to be creative inside your training of the little one. They motivate your child to participate in within the training and show the way they learn by being more productive within

  6. #6 peak

    tables and columns as well as calculating summary statistics such as means, frequency, and percentiles. Creating filters and joins on in-memory data are also discussed.Learn how to⏎Who should attendExperienced programmers who need to learn the syntax and functionality

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 just want to know the truth. For the time being, I just need to know if this is the best answer. Let me know if I can get it. So what's the answer. Now I need to know if this is

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 effects of acid precipitation on the ecological environment and restoration. Press of Chinese Environmental Sciences, Beijing, pp 1–3⏎Lei HC, Wu YX, Xiao H, Shen ZL (2001) Study on cloud

  2. #2 peak

    ⏎Lin CC, Lin XM, Zou Y, Zhang L (2005) Study on the

  3. #3 peak

    four different arcs, for a total of twelve separate images of the same galaxy!⏎Whoa. The cluster is called PSZ1 G311.65−18.48, and

  4. #4 peak

    to a long-term and repeated drought in monoculture and mixed plantings, the “Kranzberg Roof Project” (KROOF, kroof.wzw.tum.de) was initiated in 2013 and received funding by

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. L4:1651 suppresses
  2. L3:213 weakly suppresses
  3. L4:532 weakly suppresses
  4. L3:1383 weakly suppresses
  5. L5:66 weakly excites
  6. L3:893 weakly suppresses
  7. L3:156 weakly excites
  8. L5:2256 weakly suppresses
  9. L1:2306 weakly excites
  10. L0:3061 weakly excites
  11. L5:1857 weakly excites
  12. L5:1900 weakly excites
  13. L3:2218 weakly suppresses
  14. L4:2240 weakly excites
  15. L4:2848 weakly suppresses
  16. L3:3042 weakly excites
  17. L1:2350 weakly excites 'reasons' or 'permitting' after a qualifier
  18. L4:12 weakly suppresses
  19. L1:1992 weakly suppresses
  20. L4:1075 weakly suppresses
  21. L2:111 weakly suppresses
  22. L4:868 weakly excites
  23. L3:1003 weakly excites
  24. L2:3005 weakly excites

Feeds later layers

  1. L7:55 suppresses
  2. L13:645 weakly excites
  3. L17:758 weakly suppresses
  4. L23:2158 weakly excites
  5. L9:207 weakly suppresses
  6. L8:2244 weakly suppresses
  7. L24:838 weakly excites
  8. L8:200 weakly excites
  9. L18:2830 weakly excites
  10. L10:370 weakly excites
  11. L20:395 weakly suppresses
  12. L9:232 weakly suppresses
  13. L8:277 weakly excites
  14. L10:1159 weakly excites
  15. L9:281 weakly suppresses
  16. L10:2432 weakly excites
  17. L15:401 weakly excites
  18. L21:2400 weakly excites
  19. L14:1818 weakly excites
  20. L24:1165 weakly excites
  21. L17:435 weakly suppresses
  22. L24:1268 weakly excites
  23. L14:3003 weakly suppresses
  24. L16:1627 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 -2.69 and -2.552 values between -1.04 and -0.901 values between -0.76 and -0.621 values between -0.62 and -0.4917 values between -0.49 and -0.35161 values between -0.35 and -0.21805 values between -0.21 and -0.071923 values between -0.07 and 0.06794 values between 0.06 and 0.20148 values between 0.20 and 0.3427 values between 0.34 and 0.489 values between 0.48 and 0.615 values between 0.61 and 0.753 values between 0.75 and 0.892 values between 0.89 and 1.031 values between 1.03 and 1.161 values between 1.16 and 1.302 values between 1.30 and 1.442 values between 1.71 and 1.852 values between 2.54 and 2.681 values between 2.68 and 2.81offnegativepositiveoften

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. entials
  2. 郦
  3. .shuffle
  4. gether
  5. 医科大学
  6. panion
  7. 匏
  8. strength
  9. rv
  10. 鹬

Suppresses

  1. ē
  2. 台
  3. اص
  4. 节
  5. 较大的
  6. Dön
  7. agements
  8. agen
  9. chù
  10. [