Neuron Explorer

Qwen3-0.6B

'of' after a measured quantity

A neuron in layer 6 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 measurable quantity or setting, like 'a carbon price of $50', 'altitude of 8,000 feet' or 'a value of zero'. Turned up, it pushed the writing toward numbers and amounts. It goes quiet or negative on 'was' or 'is' in comparisons like 'a response time that was'.

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

    this month, may result in more legislation, or a timetable for the introduction of further curbs on emissions, for example an international carbon price. A carbon price of $50 per tonne emitted is already accounted for by some companies, C

  2. #2 peak

    a cabin altitude of 8,000 feet. Many post-abdominal surgery patients have

  3. #3 peak

    must be visible for the character to be visible.⏎The width and height of the rectangular area are determined by the⏎value of this property.⏎For example a value of zero represents a point in the center. A⏎value of a half represents a

  4. #4 peak

    a force of enlightenment and it is not only verses of the Quran that testy to that fact

  5. #5 peak

    majors. Use ANOVA – single factor in Excel’s Data Analysis ToolPak to test whether there is a relationship between the two variables. Use an alpha of 10% Show your hypotheses, ANOVA output, and decision –

  6. #6 peak

    ,190 km2 (459 sq mi) with a basal circumference of 140 km. This makes it by far the largest of the three

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 question is, which of the following is the best? The structure of the question is such that the first data set can be partitioned in a way that the first data set is a group of things. The question is, which of

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

    bound to the antibody attached to the gold film lining the array holes. When compared with established SPR-based measurement techniques, the flow-through device had a response time that was sixfold faster while measuring PAX8 present at concentrations in the attomolar

  2. #2 peak

    the indoor air quality of your home or office has an air pollution level that is 2-5 times higher than the level of the air outside its doors.⏎

  3. #3 peak

    along with a brief explanation written by a professional astronomer.⏎2000 April 21⏎Explanation: Star formation occurs at a faster pace in M82 -- a galaxy with about 10 times the rate of massive star birth

  4. #4 peak

    Earth. M81 is a spiral galaxy about 12 million light years away that is both relatively

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. L4:200 weakly excites
  2. L4:1824 weakly suppresses
  3. L4:2919 weakly excites
  4. L5:985 weakly excites
  5. L1:1399 weakly suppresses
  6. L3:408 weakly suppresses
  7. L5:1544 weakly suppresses
  8. L5:75 weakly excites
  9. L5:221 weakly excites
  10. L1:2748 weakly excites
  11. L5:117 weakly excites
  12. L3:59 weakly excites
  13. L5:102 weakly excites
  14. L3:856 weakly excites
  15. L2:483 weakly suppresses
  16. L1:2340 weakly suppresses
  17. L2:1899 weakly excites
  18. L3:833 weakly suppresses
  19. L1:146 weakly excites
  20. L5:1016 weakly excites
  21. L3:1076 weakly excites
  22. L3:105 weakly suppresses
  23. L5:222 weakly suppresses
  24. L4:350 weakly suppresses

Feeds later layers

  1. L7:582 strongly excites
  2. L10:868 excites
  3. L12:1467 excites numbers after dates and figures
  4. L8:229 excites
  5. L18:1259 excites
  6. L7:1524 excites
  7. L8:190 excites
  8. L7:79 excites
  9. L19:248 suppresses
  10. L22:481 excites
  11. L13:2034 excites
  12. L19:2450 excites
  13. L14:827 excites open bracket after a value or citation
  14. L14:1378 excites
  15. L14:471 excites
  16. L12:305 excites
  17. L24:722 excites 'about' or 'approximately' before a number
  18. L7:1742 excites
  19. L18:585 excites
  20. L20:780 excites 'of' before a measured value
  21. L23:198 excites
  22. L11:579 excites
  23. L16:1169 excites
  24. L13:287 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 -1.15 and -1.051 values between -1.05 and -0.955 values between -0.95 and -0.8410 values between -0.84 and -0.749 values between -0.74 and -0.6415 values between -0.64 and -0.5318 values between -0.53 and -0.4342 values between -0.43 and -0.33156 values between -0.33 and -0.23482 values between -0.23 and -0.121035 values between -0.12 and -0.021378 values between -0.02 and 0.08583 values between 0.08 and 0.19134 values between 0.19 and 0.2922 values between 0.29 and 0.398 values between 0.39 and 0.502 values between 0.50 and 0.602 values between 0.60 and 0.701 values between 0.70 and 0.811 values between 0.81 and 0.911 values between 0.91 and 1.011 values between 1.22 and 1.321 values between 2.87 and 2.97offnegativepositiveoften

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. 甯
  2. せい
  3. 和个人
  4. $log
  5. .Writer
  6. 客户提供
  7. ением
  8. igion
  9. PHPExcel
  10. ồ

Suppresses

  1. trag
  2. wer
  3. ebb
  4. uilt
  5. ący
  6. aket
  7. ster
  8. reak
  9. нст
  10. Zug