Neuron Explorer

Qwen3-0.6B

'of' after 'one' or 'some' (partitives)

A neuron in layer 12 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 'of' in phrases like 'one of the oldest', 'some of the most common questions' or 'some of these limitations', where a part of a group is named. It has only weak negative responses. Turning it up did not give a clear theme in the generated 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

    the world? 70% of all PET bottles are recycled here, compared to 31% in the USA. But before you give yourself a pat on the back for this achievement, can you name the invisible force behind it? It

  2. #2 peak

    of the message.⏎The Internet Acronym Server⏎This site can be used to look up the meaning of an acronym (abbreviations⏎constructed from the first letters of several words, such as ADA for⏎American Dental Association). You can also type

  3. #3 peak

    Hittites contribute to cultural diffusion?⏎How did the Hittites contribute to cultural diffusion of early Mesopotamian culture and ideas, and what was one of their important technological advances? The Hittites had learned to get iron from ore

  4. #4 peak

    sent NIH his grant application:⏎Boylan's letter made its way to Ernest M. Allen, head of NIH's fledgling Division of Research Grants and one of the key architects of the agency's peer-review grants system. "Ernest Allen

  5. #5 peak

    these criteria is nearly impossible. And the risks you’re taking by assuming it’s safety far outweigh the possible benefits of drinking raw milk.⏎Here are answers to some of the most common questions about raw milk.⏎What is raw milk?⏎Milk that

  6. #6 peak

    distances to primary markets, and vulnerability to climate change.⏎Although he confirmed the United Nations Industrial Development Organization (UNIDO) has been implementing various programmes to address some of these limitations - including introducing technical cooperation on waste management, giving assistance with building resilience

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: The function is, I think, a function that is a function from (x, ) to (0, ) is a vector, but I need to get the function. Let's see, let's take, say, (x)

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

    in the Ussr. StudyMode.com. Retrieved 05, 2012, from http://www.studymode.com/essays/The-Struggle-For-Power-In-The-99432

  2. #2 peak

    flowers. Stems have vascular tissues that move food and water around the plant to help it grow. They are also used as a place to store food.⏎Image: amenic181/Getty Images⏎Roots grow underground and gather water and

  3. #3 peak

    mynursingpaper.com/wp-content/uploads/2020/06/cropped-15597

  4. #4 peak

    and culturally sensitive manner. Privacy is essential and the nurse must be aware of their own ...⏎You have reached your viewing limit for this book.⏎What people are saying - Write a review⏎Respiratory system 52 Thoracotomy⏎St

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. L10:272 suppresses
  2. L4:16 weakly excites
  3. L8:1003 weakly suppresses "the" or "of" before a noun phrase
  4. L8:137 weakly suppresses
  5. L8:892 weakly excites
  6. L9:836 weakly excites
  7. L9:734 weakly excites
  8. L4:24 weakly excites
  9. L10:2717 weakly suppresses
  10. L11:2057 weakly excites
  11. L8:252 weakly suppresses 'of' after 'each' or 'one' or 'all'
  12. L7:2218 weakly suppresses
  13. L11:293 weakly suppresses
  14. L3:2116 weakly excites
  15. L8:1101 weakly suppresses
  16. L1:408 weakly excites
  17. L11:473 weakly suppresses
  18. L8:437 weakly suppresses
  19. L6:1169 weakly suppresses
  20. L2:2957 weakly excites
  21. L8:328 weakly excites
  22. L10:779 weakly excites
  23. L2:1036 weakly excites
  24. L4:1842 weakly suppresses

Feeds later layers

  1. L14:655 strongly excites
  2. L16:1219 excites
  3. L19:695 suppresses
  4. L18:977 excites
  5. L15:1283 excites
  6. L19:2385 excites
  7. L17:1250 excites
  8. L16:528 excites
  9. L15:1702 excites
  10. L17:2736 excites
  11. L15:1028 excites
  12. L17:2702 excites
  13. L13:844 excites 'of' after a percentage or share
  14. L18:552 suppresses
  15. L18:748 excites
  16. L18:520 excites
  17. L15:1033 excites
  18. L18:1199 excites
  19. L18:315 suppresses
  20. L18:867 excites
  21. L15:2740 excites
  22. L17:865 excites
  23. L13:2116 excites
  24. L14:1588 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 -0.63 and -0.577 values between -0.57 and -0.5015 values between -0.50 and -0.4330 values between -0.43 and -0.3785 values between -0.37 and -0.30159 values between -0.30 and -0.23370 values between -0.23 and -0.16508 values between -0.16 and -0.10696 values between -0.10 and -0.03830 values between -0.03 and 0.04564 values between 0.04 and 0.11333 values between 0.11 and 0.17177 values between 0.17 and 0.2480 values between 0.24 and 0.3128 values between 0.31 and 0.3711 values between 0.37 and 0.442 values between 0.44 and 0.512 values between 0.51 and 0.573 values between 0.57 and 0.641 values between 0.71 and 0.782 values between 0.78 and 0.841 values between 0.84 and 0.911 values between 0.91 and 0.981 values between 1.71 and 1.781 values between 1.98 and 2.05offnegativepositiveoften

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. __(*
  2. /Gate
  3. пед
  4. legate
  5. .reserve
  6. __ ⏎
  7. ällt
  8. öße
  9. culator
  10. loat

Suppresses

  1. R
  2. ne
  3. 变化
  4. 灵活
  5. ur
  6. mer
  7. D
  8. N
  9. 렴
  10. in