Neuron Explorer

Qwen3-0.6B

'of' after a job title

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 fires on the word 'of' when it follows a job title, such as 'chief of', 'professor of' or 'director of'. Turning it up did not produce a clear theme in the written text, so its effect on the writing is hard to read.

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 Hispanic children have close to double the rate of obesity in comparison to white children in the U.S.,” says Dr. Elsie Taveras, chief of General Pediatrics at Mass General Hospital. “The behavioral risk factors during<|endoftext|>An Australian

  2. #2 peak

    "A landmark study on one of the most pressing problems facing society, balancing economic growth and ecological protection to achieve a sustainable future."⏎- Simon Levin, Moffett Professor of Biology, Department of Ecology and Evolution Behaviour, Princeton

  3. #3 peak

    not as simplistic as we've tended to imagine," says study co-author T.R. Kidder, PhD, professor and chair of anthropology in Arts and Sciences at Washington University in St. Louis.⏎"Our findings

  4. #4 peak

    protein modification. These tumor samples consistently tied to worse outcomes in children, suggesting a critical marker for predicting prognosis.⏎What's more, the researchers found that simple immunohistochemical staining methods in tumor biopsy samples can show whether the tumor has high or

  5. #5 peak

    of Music, University of Chicago⏎—Anthony Cascardi, University of California, Berkeley⏎—Jesse J. Prinz, John J. Rogers Professor of Philosophy, University of North Carolina, and author of Furnishing the Mind: Concepts

  6. #6 peak

    , including the number of the unique words and a list of the most frequent words, a Corpus Reader that lets you see all your text and select certain words and highlights

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 am a woman of many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many many

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

    this question⏎Join a community of thousands of dedicated teachers and students.Join eNotes<|endoftext|>Is there something else you would like to know?⏎Use the alphabetical glossary listing to find a short definition to a medical or dental term. If you would like

  2. #2 peak

    services and evaluate video quality in six categories of digital defects on a scale of one to five (one being unwatchable and five being spectacular).”⏎“In addition, Comcast is working to establish local golden-eye programs

  3. #3 peak

    , but it also determines your blood type. There are two main blood groups, the ABO group and the Rh group. The ABO group is made up of A,

  4. #4 peak

    .⏎A thin layer of tissue is excised from<|endoftext|>In computer programming, a Either-OR is used as an OR operator to choose a value between 2 values. Either of Two words are often used to represent the truth value of a statement

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. L10:2958 excites
  2. L10:1707 excites
  3. L7:1094 weakly suppresses
  4. L10:2012 weakly suppresses
  5. L9:1491 weakly suppresses
  6. L3:2478 weakly excites
  7. L10:1996 weakly excites
  8. L9:996 weakly excites
  9. L9:2257 weakly suppresses
  10. L8:2399 weakly suppresses
  11. L5:256 weakly excites
  12. L8:2573 weakly excites
  13. L4:978 weakly excites
  14. L10:2092 weakly suppresses
  15. L7:179 weakly suppresses
  16. L0:3047 weakly suppresses
  17. L2:1446 weakly suppresses
  18. L9:728 weakly suppresses
  19. L4:2504 weakly excites
  20. L7:2066 weakly excites unclear: technical word fragments, mostly engineering
  21. L8:2624 weakly suppresses
  22. L9:1416 weakly excites
  23. L10:2561 weakly suppresses
  24. L10:745 weakly suppresses

Feeds later layers

  1. L15:1163 excites
  2. L12:1311 suppresses
  3. L16:2938 suppresses
  4. L13:246 excites
  5. L15:2696 weakly excites
  6. L14:1670 weakly excites
  7. L12:301 weakly suppresses
  8. L16:1131 weakly suppresses
  9. L18:2108 weakly suppresses
  10. L12:1962 weakly excites
  11. L12:1794 weakly suppresses
  12. L15:1140 weakly excites
  13. L14:433 weakly excites
  14. L12:2464 weakly suppresses
  15. L12:1681 weakly excites
  16. L13:721 weakly suppresses
  17. L12:1085 weakly suppresses
  18. L18:2492 weakly suppresses
  19. L17:2681 weakly suppresses
  20. L12:2702 weakly excites
  21. L12:2019 weakly excites
  22. L23:2687 weakly suppresses
  23. L16:1863 weakly excites
  24. L14:2433 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 -2.72 and -2.581 values between -1.60 and -1.461 values between -1.46 and -1.323 values between -1.32 and -1.181 values between -1.18 and -1.047 values between -1.04 and -0.908 values between -0.90 and -0.7613 values between -0.76 and -0.6230 values between -0.62 and -0.4854 values between -0.48 and -0.34151 values between -0.34 and -0.20475 values between -0.20 and -0.061676 values between -0.06 and 0.08703 values between 0.08 and 0.22326 values between 0.22 and 0.36187 values between 0.36 and 0.50105 values between 0.50 and 0.6546 values between 0.65 and 0.7938 values between 0.79 and 0.9334 values between 0.93 and 1.0710 values between 1.07 and 1.2116 values between 1.21 and 1.356 values between 1.35 and 1.494 values between 1.49 and 1.635 values between 1.63 and 1.771 values between 1.77 and 1.914 values between 1.91 and 2.051 values between 2.61 and 2.751 values between 2.75 and 2.89offnegativepositiveoften

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. essional
  2. @return
  3. Poster
  4. ieder
  5. ready
  6. 折扣
  7. зол
  8. getRequest
  9. icz
  10. 撞击

Suppresses

  1. аниз
  2. angement
  3. 芒
  4. eson
  5. 拉斯
  6. 芙
  7. ItemCount
  8. ас
  9. ocrin
  10. Ars