Neuron Explorer

Qwen3-0.6B

"(" before a year in citations

A neuron in layer 7 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

Fires on the opening bracket in reference lists, right before the year of a citation, such as "Kunkel, A. (2010)". Turning it down or up did not produce any clear theme in the writing.

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

    . 37–47)⏎Preston, J. D., O’Neal, J. H., & Talaga, M. C. (2017). Handbook of clinical psychopharmacology for therapists (8

  2. #2 peak

    : Gwartney, J. D., Stroup, R. L., Sobel, R. S., & Macpherson, D. A. (2018). Economics: Private⏎and public choice (16

  3. #3 peak

    photography studio that Dalmau opened in 1854.⏎Download data is not yet available.⏎How to Cite⏎Cuenca, C. (2019). The The “Animated Polystereoscope

  4. #4 peak

    provides an example of a revised “show-me” sentence and six exercises for students to practice.|⏎Baines, L., & Kunkel, A. (2010). Going bohemian

  5. #5 peak

    .⏎McLaren, P., & Farahmandpur, R. (2001). Class, Cultism, and Multiculturalism. Mult

  6. #6 peak

    ., Lo, C.-M., Chan, K. S.-C., Chan, D. W.-O., & Chung, K. K.-H. (2014, July). Effectiveness of a tiered intervention model in

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 numbers. I know that the numbers are the numbers, the numbers. So, if you have a number of coins, then, for example, they are in a certain quantity, and I know that I have them. So, the

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

    date. The kids love to play with these sound shakers. So, now it’s your turn to make this easy

  2. #2 peak

    time should focus on four critical areas: (1) developing understanding of and applying proportional relationships; (2) developing understanding of operations with rational numbers and working with expressions and linear equations; (3) solving problems involving

  3. #3 peak

    were laser cut (bottom right).⏎Task: For this final project exercise, students were given the constraint of working with a common and uncommon design material. The team highlighted in this example were given wood

  4. #4 peak

    the formulas that we have used so far.⏎- Just be careful about using the correct sign (positive or negative) depending on the problem.⏎Examples of Calculations with Gravity⏎Example 1: A ball is thrown up into the air at an

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. L5:2952 excites
  2. L5:1929 weakly suppresses
  3. L6:903 weakly suppresses
  4. L5:2081 weakly excites
  5. L3:1708 weakly suppresses
  6. L6:2409 weakly excites
  7. L5:1810 weakly suppresses
  8. L5:2934 weakly excites
  9. L3:680 weakly suppresses
  10. L6:2042 weakly suppresses
  11. L6:2827 weakly excites
  12. L1:608 weakly excites
  13. L1:1888 weakly suppresses
  14. L3:2480 weakly excites
  15. L5:1368 weakly suppresses
  16. L4:1829 weakly excites
  17. L1:2467 weakly suppresses
  18. L6:2434 weakly suppresses
  19. L0:223 weakly suppresses
  20. L4:3049 weakly suppresses
  21. L2:2892 weakly suppresses
  22. L4:2533 weakly excites
  23. L1:2801 weakly excites
  24. L2:892 weakly suppresses

Feeds later layers

  1. L8:685 excites
  2. L21:1907 suppresses
  3. L22:2312 suppresses
  4. L12:2888 weakly suppresses
  5. L12:2737 weakly suppresses
  6. L9:1909 weakly suppresses
  7. L24:1984 weakly suppresses
  8. L8:2960 weakly suppresses
  9. L23:461 weakly suppresses
  10. L24:2941 weakly excites
  11. L11:99 weakly suppresses
  12. L10:552 weakly excites
  13. L8:2357 weakly suppresses
  14. L9:521 weakly excites
  15. L10:2624 weakly suppresses
  16. L10:2542 weakly excites "is" after "it" in advice phrasing
  17. L13:1729 weakly suppresses
  18. L17:2539 weakly suppresses
  19. L9:1964 weakly suppresses
  20. L12:1107 weakly excites
  21. L16:1553 weakly suppresses
  22. L20:1955 weakly suppresses
  23. L22:2139 weakly suppresses
  24. L23:1837 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 -4.14 and -3.961 values between -1.88 and -1.701 values between -1.70 and -1.532 values between -1.53 and -1.351 values between -1.35 and -1.181 values between -1.18 and -1.015 values between -0.83 and -0.669 values between -0.66 and -0.4842 values between -0.48 and -0.31277 values between -0.31 and -0.141736 values between -0.14 and 0.041460 values between 0.04 and 0.21336 values between 0.21 and 0.3927 values between 0.39 and 0.564 values between 0.56 and 0.743 values between 0.74 and 0.911 values between 1.26 and 1.431 values between 2.65 and 2.82offnegativepositiveoften

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. сен
  2. 正品
  3. Comparer
  4. psychiatrist
  5. 早早
  6. 购车
  7. IFICATION
  8. Comparison
  9. 正版
  10. 独立董事

Suppresses

  1. aths
  2. manipulating
  3. mk
  4. gon
  5. alie
  6. (Scene
  7. lửa
  8. manip
  9. omon
  10. 还想