Neuron Explorer

Qwen3-0.6B

page and volume numbers in citations

A neuron in layer 13 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 spot right before page or volume numbers in bibliography entries, such as after "pp." or after a journal volume. The negative side fires inside names and words, like the apostrophe in a spacecraft name. Turning it up made the model write repetitive or filler text that does not clearly show this pattern.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    "Purchasing Power Parity Exchange Rates for the Global Poor,"⏎American Economic Journal: Applied Economics,⏎American Economic Association, vol. 3(2), pages 137-66, April.⏎- Angus Deaton & Olivier Dup

  2. #2 peak

    "Purification Study of Pervious Concrete Pavbement," International Journal of Engineering and Technology vol. 5, no. 5, pp. 532-535, 2013.<|endoftext|>Following

  3. #3 peak

    1722. This text is based on Kessinger Publishing's facsimile (ISBN 0-7661-6894-8) of J. and P. Knapton's edition of 1

  4. #4 peak

    in Education (eJSiE):⏎2, Article 1.⏎Available at: http://epublications.bond.edu.au/ejsie/vol8/iss2/1<|endoftext|>Some may argue that sleeping is one of the best parts

  5. #5 peak

    Contrasting response of native and non‐native plants to disturbance and herbivory in mountain environments. Journal of Biogeography, 48(7), 1594-1605 https://doi.org/10

  6. #6 peak

    the board exams. Students can easily NCERT Solutions for Class 10 Maths Exercise 6.5 Chapter 6 Triangles from below.⏎CBSE Class 10 Maths Chapter 6 Triangles Exercise 6.5 Solutions⏎Topics

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 told that I have been given a question and I have been told that I have been given a question that is worth 1000, and I have been given a question that is worth 1000,

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

    moon that we earthlings don’t see and has yet to be studied—that is, until now.⏎On January 3rd, China’s spacecraft called the Chang’e 4 made a soft landing on the dark side of the moon. Its mission

  2. #2 peak

    -reaching consequences.⏎In addition to being as a major milestone in the history of astronomy and the study of Deep Sky Objects. One of these objects is known as Messier 10 (aka. NGC 6254), a glob

  3. #3 peak

    , 2, 3, 4, 5] i = len(given_arr) - 1 while(i >= 0): print(given_arr[i]) i = i - 1⏎In this program,⏎- given_arr

  4. #4 peak

    tapered edge. The positive side, or anode, typically has no marking.⏎Decode the diode type and material designation. This is designated by the "1N" in the part number. The "1" identifies the component as a di

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. L9:884 excites
  2. L8:2591 excites
  3. L12:752 excites
  4. L10:574 excites
  5. L6:371 suppresses
  6. L9:1108 suppresses
  7. L10:2461 excites
  8. L12:1301 excites
  9. L12:1809 suppresses
  10. L12:2110 suppresses
  11. L11:1218 suppresses
  12. L12:713 excites
  13. L0:2404 excites
  14. L6:1469 weakly excites
  15. L12:2956 weakly suppresses
  16. L4:973 weakly suppresses
  17. L10:281 weakly excites
  18. L11:293 weakly suppresses
  19. L12:1319 weakly suppresses
  20. L12:2168 weakly excites
  21. L12:1496 weakly excites
  22. L11:2835 weakly excites
  23. L8:350 weakly suppresses blank space before a year
  24. L5:2869 weakly excites

Feeds later layers

  1. L15:958 suppresses
  2. L17:1744 suppresses
  3. L14:1542 excites
  4. L14:677 excites
  5. L17:1806 suppresses
  6. L15:1041 excites
  7. L17:163 suppresses
  8. L16:2099 suppresses
  9. L17:202 excites
  10. L16:2059 suppresses
  11. L15:42 suppresses
  12. L14:1094 suppresses
  13. L17:354 suppresses
  14. L18:92 suppresses
  15. L16:302 suppresses
  16. L18:352 suppresses
  17. L15:748 weakly suppresses
  18. L17:932 weakly suppresses
  19. L14:193 weakly excites
  20. L16:2148 weakly suppresses
  21. L15:289 weakly excites
  22. L17:222 weakly suppresses
  23. L14:371 weakly excites
  24. L14:453 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.

1 values between -3.93 and -3.813 values between -2.64 and -2.521 values between -2.52 and -2.401 values between -1.46 and -1.343 values between -0.64 and -0.525 values between -0.52 and -0.4046 values between -0.40 and -0.29249 values between -0.29 and -0.17818 values between -0.17 and -0.051543 values between -0.05 and 0.07875 values between 0.07 and 0.18249 values between 0.18 and 0.3077 values between 0.30 and 0.4229 values between 0.42 and 0.547 values between 0.54 and 0.651 values between 0.65 and 0.77offnegativepositiveoften

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. ertext
  2. rots
  3. possible
  4. (Set
  5. арт
  6. ETS
  7. SAT
  8. ropriate
  9. PT
  10. elman

Suppresses

  1. 发生了
  2. 决定了
  3. HasKey
  4. 发生
  5. 凡是
  6. washer
  7. oplay
  8. 發生
  9. ()}}⏎
  10. 涵盖了