Neuron Explorer

Qwen3-0.6B

"of" in time-span phrases

A neuron in layer 2 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 about a span of time or extent, like "period of time", "a long period of" or "single layer of". The negative side fires on odd hyphen pieces in numbers and compound words. Turning it up did not produce a clear change 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

    fatty acids attract each other to the inside of the layer and the hydrophilic ends are on the outside of the membrane in the water, creating a double layer of fatty acids⏎How are bacterial species identified?⏎Cell and colony morphology, chemical composition

  2. #2 peak

    deep waters off the coasts of<|endoftext|>Antireflective coatings consisting of a single layer of glass with a graded variation in refractive index offer advantages over multi-layer coatings.

  3. #3 peak

    do have limitations. Cell phones have only been around for about 20 years, so the studies haven’t been able to follow people over a really long period of time. Also, there haven’t been any good studies looking at the effect of

  4. #4 peak

    26th Illinois Volunteers regiment and was commissioned as Captain on August 10, 1861 by Governor Richard Yates. After less than a month of service, Tinkham was promoted to Lieutenant Colonel on August 31,

  5. #5 peak

    the employment landscape of the industry. James Cook University professor Ian Atkinson said it was likely some jobs would be lost but expected it to happen over a long period of time.⏎“It’s not just taking workers out and putting a machine in, it

  6. #6 peak

    and seasons⏎In the task sheet 2, students are reminded that 'climate' refers to the average, or typical, weather conditions observed over a long period of time for a given area. It is determined by factors such as latitude (amount

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 idea that, if you have a time series that is in the format of the United States, and you have to take into account of the number of people, and the amount of work, and the level of efficiency, and the number

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

    along a 100-kilometer long north-south linear vent system over the past 5 million years

  2. #2 peak

    and wheat acreage in Georgia is dropping.⏎To boost the state’s wheat industry and help producers get more out of their crop, University of Georgia Cooperative Extension small-grains specialist Reagan Noland is researching a dual-use system

  3. #3 peak

    Beach and Broward counties. The C-51 Basin in western Palm Beach County experienced a 1-in-100-year rainfall event with nearly 15 inches of rain over

  4. #4 peak

    that can detect biomolecules of interest without requiring the additional use of an optical label. They used a tightly focused laser to drill holes through a 100-nanometer-thick layer of gold deposited on a 100-nan

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. L1:861 weakly suppresses
  2. L1:712 weakly excites
  3. L1:231 weakly suppresses
  4. L1:951 weakly excites
  5. L1:2126 weakly excites
  6. L0:1182 weakly excites
  7. L1:1322 weakly excites
  8. L0:2705 weakly excites
  9. L1:1152 weakly suppresses
  10. L1:1096 weakly suppresses
  11. L1:1417 weakly suppresses
  12. L0:2243 weakly excites
  13. L0:1836 weakly suppresses
  14. L0:0 weakly excites
  15. L1:262 weakly excites
  16. L1:1244 weakly suppresses "of" after "board" or "off"
  17. L0:2179 weakly excites
  18. L1:468 weakly excites
  19. L0:5 weakly excites
  20. L1:74 weakly excites
  21. L1:898 weakly excites
  22. L0:2914 weakly suppresses
  23. L1:1126 weakly suppresses
  24. L0:2854 weakly suppresses

Feeds later layers

  1. L6:1195 suppresses
  2. L12:575 weakly suppresses
  3. L3:750 weakly excites
  4. L19:2369 weakly suppresses
  5. L9:1163 weakly suppresses
  6. L14:298 weakly excites
  7. L8:386 weakly suppresses
  8. L6:1063 weakly suppresses
  9. L9:1165 weakly suppresses
  10. L16:2153 weakly suppresses
  11. L25:67 weakly excites
  12. L13:1365 weakly suppresses
  13. L7:1313 weakly suppresses
  14. L9:2838 weakly excites
  15. L11:469 weakly suppresses
  16. L15:1549 weakly suppresses
  17. L6:350 weakly suppresses
  18. L3:492 weakly excites
  19. L8:359 weakly suppresses
  20. L3:195 weakly excites
  21. L7:2159 weakly suppresses
  22. L15:2308 weakly excites
  23. L12:696 weakly suppresses
  24. L20:1611 weakly 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 -3.65 and -3.521 values between -2.06 and -1.921 values between -1.52 and -1.392 values between -1.39 and -1.261 values between -1.26 and -1.124 values between -1.12 and -0.992 values between -0.99 and -0.861 values between -0.86 and -0.733 values between -0.73 and -0.594 values between -0.59 and -0.4615 values between -0.46 and -0.3369 values between -0.33 and -0.19646 values between -0.19 and -0.062462 values between -0.06 and 0.07584 values between 0.07 and 0.2177 values between 0.21 and 0.3411 values between 0.34 and 0.4711 values between 0.47 and 0.618 values between 0.61 and 0.742 values between 0.74 and 0.871 values between 0.87 and 1.011 values between 1.01 and 1.141 values between 1.54 and 1.67offnegativepositiveoften

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. ienne
  2. UCH
  3. ellular
  4. <Token
  5. уча
  6. hiệp
  7. ATTERN
  8. atty
  9. ично
  10. #:

Suppresses

  1. الرسمي
  2. ofs
  3. CAM
  4. -pagination
  5. abcdefgh
  6. 发展潜力
  7. obar
  8. anner
  9. 不一样
  10. emple