Neuron Explorer

Qwen3-0.6B

'of' in fixed phrases like table of contents

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 set phrases such as 'Table of Contents', 'range of movement', 'field of view', and 'proof of concept'. It fires weakly or not at all on other words. Turning it up did not make the writing about any single topic.

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

    plant care tips to help you efficiently care for and grow this plant’s root system.⏎Table of Contents⏎The family of Medusa Head Plants contains more than three hundred varieties of

  2. #2 peak

    by University of Minnesota students. You can see all of the details involved in making it in the video below.<|endoftext|>Create a Graph⏎Library Home || Full Table of Contents || Suggest a Link || Library Help⏎|National Center for Education Statistics

  3. #3 peak

    and uncover the remarkable ways in which they assist us in diagnosing and managing our health.⏎Table of Contents⏎Cancer is a disease that affects millions of people worldwide. It is

  4. #4 peak

    <|endoftext|>FROM ISSUE NUMBER 15 ~ SPRING 2013 GO TO TABLE OF CONTENTS⏎The Art of Limited Government⏎In his first inaugural address, Thomas

  5. #5 peak

    you how to weld pipe correctly. By the end, you will be able to start preparing as a pipe welder and having joints that pass stress tests.⏎Table of Contents⏎- 1 How welding works⏎- 2 Which welding is best

  6. #6 peak

    time during a comets apparition even⏎binoculars will be too powerful...⏎A telescope is a big mistake, it will have much too narrow a field of view.⏎Please, you should not just go out to an unfamiliar rural "dark

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: what is the value of the expression $f(f(f(f(x)))$ evaluated at x? when the input is processed through four different functions, and then the output is processed again through four different functions, and the expression is evaluated again at

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

    ask a parent or adult before you fill out any forms, or give out money or credit card details.⏎- Don't accept any offers that seem too good to be true - they probably are.⏎Remember to always be

  2. #2 peak

    when you're online to keep your identity safe.⏎- Only Make Purchases On Trusted Sites⏎When deals seem too good to be true, they just may be - you might be paying as a victim of identity

  3. #3 peak

    Fukushima, ...) and model assessment using single effect tests or integrated experiments (QUENCH, PARAMETER, ...).⏎In the SACRE group SCDAP/RELAP5 is used for core degradation calculations and model assessment using single effect tests or integrated

  4. #4 peak

    schools must meet graduation goals and middle and elementary schools must meet a third academic indicator. Schools and districts that miss goals are identified for improvement.⏎Visit the Adequate Yearly Progress Page⏎Federal law requires states, school districts, and schools to produce

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. L11:393 strongly excites
  2. L10:1705 strongly excites
  3. L9:746 strongly suppresses
  4. L8:1480 strongly suppresses
  5. L10:2514 strongly suppresses
  6. L10:952 strongly excites
  7. L7:2370 strongly suppresses
  8. L6:2164 strongly suppresses second half of multi-word proper names
  9. L10:2510 strongly suppresses
  10. L8:849 strongly suppresses
  11. L10:2105 strongly suppresses
  12. L8:1976 strongly suppresses
  13. L11:1384 strongly suppresses
  14. L9:1276 strongly excites
  15. L9:845 strongly excites
  16. L10:129 strongly suppresses
  17. L10:1784 excites
  18. L9:2613 suppresses
  19. L8:2388 suppresses
  20. L10:2035 suppresses
  21. L8:852 suppresses comma inside large numbers
  22. L7:1684 excites
  23. L9:716 excites
  24. L9:2392 suppresses

Feeds later layers

  1. L17:1042 strongly excites
  2. L15:646 strongly excites
  3. L13:1929 strongly excites
  4. L13:450 strongly suppresses
  5. L19:2411 strongly excites
  6. L20:1292 strongly excites
  7. L14:1403 strongly excites
  8. L18:558 excites
  9. L19:1432 excites
  10. L15:966 excites
  11. L15:1964 excites
  12. L19:107 suppresses
  13. L16:2117 excites
  14. L19:1385 excites
  15. L18:151 suppresses
  16. L18:819 excites
  17. L20:118 excites
  18. L17:533 excites
  19. L13:738 excites
  20. L14:528 excites
  21. L20:452 suppresses
  22. L18:708 excites
  23. L18:1165 excites
  24. L15:227 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 -12.65 and -12.241 values between -11.84 and -11.431 values between -10.62 and -10.211 values between -8.59 and -8.181 values between -6.56 and -6.162 values between -5.34 and -4.941 values between -4.94 and -4.534 values between -4.13 and -3.721 values between -3.72 and -3.312 values between -3.31 and -2.912 values between -2.91 and -2.501 values between -2.50 and -2.104 values between -2.10 and -1.698 values between -1.69 and -1.2811 values between -1.28 and -0.8898 values between -0.88 and -0.472684 values between -0.47 and -0.07938 values between -0.07 and 0.3480 values between 0.34 and 0.7537 values between 0.75 and 1.1518 values between 1.15 and 1.564 values between 1.56 and 1.963 values between 1.96 and 2.372 values between 2.37 and 2.772 values between 2.77 and 3.181 values between 3.18 and 3.59offnegativepositiveoften

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. ycastle
  2. .force
  3. .),
  4. .").
  5. PCS
  6. 纣
  7. 商会
  8. Merc
  9. бу
  10. .Factory

Suppresses

  1. ting
  2. agnostics
  3. uated
  4. irmed
  5. above
  6. hoot
  7. NING
  8. 走
  9. ning
  10. ging