Neuron Explorer

Qwen3-0.6B

"of" after a measurement noun

A neuron in layer 1 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 measurement word such as "rate", "temperature", "resolution" or "capacity", as in "a flow rate of 16 l/min". Turning it up did not make the model's writing clearly about measurements.

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

    argon and 5% CO 2 gas mixture at a flow rate of 16 l/min was used for shielding throughout the welding.⏎Some of fab

  2. #2 peak

    year in Mount Surprise is 73.0°F (22.8°C). The warmest month, on average, is November with an average temperature of 81.0°F (27.2°C). The coolest month

  3. #3 peak

    asa said.⏎Colors of Mercury⏎The project is part of a global color map that covers more than 99% of Mercury’s surface with an average resolution of about 1 kilometer per pixel. The view here is what an observer would

  4. #4 peak

    the image has a resolution of about 70 meters (230 feet) per pixel. This image

  5. #5 peak

    what you want your error of tolerance to be. For example, you may be happy with a confidence level of 95 percent (giving a margin error of 0.05), or you may require a tighter accuracy of a

  6. #6 peak

    taken in visible light with the Cassini spacecraft narrow-angle camera on Jan. 22, 2008. The view was obtained at a distance of approximately 1.7 million kilometers (1.1 million miles) from Prometheus

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 have been thinking about lately, and I have been thinking about lately. How do you think about lately? How do you think about lately? How do you think about lately? The question is about how I have been thinking about lately,

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

    global event day and raise the profile of cancer in people’s minds and in the world’s media

  2. #2 peak

    be 99,800 unaffected pregnancies and 200 pregnancies with Down syndrome. The table below compares the results of the most commonly used biochemical screening test (

  3. #3 peak

    of heat.⏎Made of shredded newspaper and a fire retardant chemical (borate), the paper is broken down into cellular fibers.⏎WHAT

  4. #4 peak

    . Election day was largely peaceful and approximately 81% of voters cast ballots, one of

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. L0:1224 suppresses
  2. L0:178 suppresses
  3. L0:1301 suppresses
  4. L0:93 weakly suppresses
  5. L0:1211 weakly excites
  6. L0:2296 weakly excites
  7. L0:250 weakly suppresses
  8. L0:2799 weakly suppresses
  9. L0:2916 weakly excites
  10. L0:2751 weakly suppresses
  11. L0:638 weakly suppresses
  12. L0:1950 weakly excites
  13. L0:1672 weakly suppresses
  14. L0:265 weakly suppresses
  15. L0:788 weakly suppresses
  16. L0:267 weakly excites
  17. L0:1715 weakly excites
  18. L0:1654 weakly excites
  19. L0:2828 weakly suppresses
  20. L0:1527 weakly excites
  21. L0:1826 weakly suppresses
  22. L0:2299 weakly excites
  23. L0:3031 weakly suppresses
  24. L0:1583 weakly excites

Feeds later layers

  1. L3:312 excites
  2. L12:1570 excites
  3. L18:585 excites
  4. L11:105 weakly suppresses
  5. L10:1034 weakly excites
  6. L18:2737 weakly suppresses
  7. L4:106 weakly excites
  8. L18:2991 weakly excites
  9. L21:175 weakly excites
  10. L19:1219 weakly excites
  11. L24:722 weakly excites 'about' or 'approximately' before a number
  12. L14:840 weakly excites
  13. L3:540 weakly excites
  14. L8:1500 weakly excites
  15. L24:1394 weakly excites
  16. L19:1947 weakly excites
  17. L12:1467 weakly excites numbers after dates and figures
  18. L22:1497 weakly suppresses
  19. L10:868 weakly excites
  20. L6:1214 weakly suppresses
  21. L6:231 weakly excites
  22. L15:828 weakly excites
  23. L11:2896 weakly suppresses
  24. L19:1888 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.

2 values between -0.74 and -0.691 values between -0.69 and -0.646 values between -0.64 and -0.588 values between -0.58 and -0.536 values between -0.53 and -0.4812 values between -0.48 and -0.4215 values between -0.42 and -0.3716 values between -0.37 and -0.3236 values between -0.32 and -0.2683 values between -0.26 and -0.21158 values between -0.21 and -0.16331 values between -0.16 and -0.10633 values between -0.10 and -0.051226 values between -0.05 and 0.00884 values between 0.00 and 0.06304 values between 0.06 and 0.11101 values between 0.11 and 0.1655 values between 0.16 and 0.2217 values between 0.22 and 0.275 values between 0.27 and 0.322 values between 0.32 and 0.381 values between 0.43 and 0.483 values between 0.53 and 0.591 values between 0.64 and 0.691 values between 0.69 and 0.751 values between 1.33 and 1.39offnegativepositiveoften

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. amento
  2. 不低于
  3. abilities
  4. 第一百
  5. 旬
  6. 睡
  7. atisf
  8. ativity
  9. lickr
  10. riott

Suppresses

  1. ichern
  2. 身上
  3. eling
  4. Hast
  5. 手上
  6. ˣ
  7. 담
  8. helm
  9. oval
  10. whole