Neuron Explorer

Qwen3-0.6B

'of' linking a noun to a larger whole

A neuron in layer 13 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 responds to the word "of" when it attaches a part or member to a bigger thing, like "atmosphere of the sun" or "crew of the ship". The effect is weaker than the neighbouring "of" neuron, and turning it up or down did not produce a clear change in the text.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    writer at Scientific American covering paleontology, archaeology and life sciences. Follow on Twitter⏎PALEO DIET: Analyses of tartar on the teeth of Australopithecus sediba show that this early human species ate bark and

  2. #2 peak

    using images from its Large Angle and Spectrometric Coronagraph (LASCO) instrument. LASCO is used to observe the faint, multimillion-degree outer atmosphere of the sun, called the corona. A disk in the instrument is used to

  3. #3 peak

    their atmospheres. The recent discovery by the Webb Telescope, notably thanks to the NIRSpec instrument, built by Airbus, of methane and carbon dioxide in the atmosphere of K2-18b, an exoplanet 8.6 times

  4. #4 peak

    must turn sideways to squeeze between them.⏎Most of the fishermen who sail the pirogues are not from Joal. Take, for example, the crew of the 69-foot-long Mansor Sakho (she is painted sky blue

  5. #5 peak

    September, students at the New Albany club were selected to pilot the program locally.⏎Time Warner Cable — parent company of Insight Communications — partnered with Boys & Girls Club of America and FIRST Robotics to bring the program to 20 chapters across the country

  6. #6 peak

    plain why these words were put in the following sequence:⏎moral, friend, port, feet, race⏎AnswerBy adding the sound of the first five letters of the alphabet to the beginning of each word respectively, another word can be enunc

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 had 200,000,000,000,000,000,000,000,000,00,0,0,0

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

    theria. If you are infected, you may infect others for up to 4 weeks. Take precautions, even if you do not have symptoms of diphtheria. Do not let anyone use your drinking cup. Everyone who lives with you

  2. #2 peak

    that is transmitted.⏎There are two different types of Low E coatings: passive Low E coatings and solar control Low E coatings.⏎The simplest way to see if your windows haveLow E glass is to hold a lit flame (match, lighter) next

  3. #3 peak

    /a0 and a0 is the Bohr radius (5.29 × 10-11 m). Calculate the position of the nodes for this wave function. Write the expected electron configurations for the following atoms: Sc, Fe,

  4. #4 peak

    01,1 requires a substantial reduction in emissions from all heavy-duty vehicle engines by 2007 through a two-pronged approach-ultra-low sulfur diesel fuel and exhaust treatment systems. While clean diesel refiners are still working on

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. L12:1653 suppresses
  2. L12:2611 excites
  3. L6:1182 suppresses "of" after a noun phrase
  4. L11:1400 excites
  5. L11:2387 weakly suppresses
  6. L9:931 weakly suppresses
  7. L12:1301 weakly excites
  8. L10:574 weakly excites
  9. L11:1396 weakly suppresses
  10. L1:2789 weakly suppresses
  11. L12:2416 weakly excites
  12. L12:850 weakly excites
  13. L12:626 weakly excites
  14. L11:98 weakly suppresses
  15. L11:3062 weakly suppresses
  16. L11:1340 weakly suppresses
  17. L11:556 weakly excites
  18. L9:1909 weakly excites
  19. L9:884 weakly excites
  20. L12:3035 weakly excites
  21. L12:1738 weakly excites
  22. L11:1731 weakly excites
  23. L11:2155 weakly excites
  24. L8:429 weakly excites

Feeds later layers

  1. L14:1191 suppresses
  2. L14:2861 suppresses 'of' after a percentage
  3. L14:2241 suppresses
  4. L14:1317 suppresses
  5. L15:2811 suppresses
  6. L14:2694 suppresses
  7. L18:2370 suppresses
  8. L19:241 excites
  9. L19:1985 weakly suppresses
  10. L16:691 weakly excites
  11. L15:2998 weakly suppresses
  12. L15:1877 weakly suppresses
  13. L17:900 weakly excites
  14. L15:2877 weakly suppresses
  15. L14:53 weakly excites
  16. L15:1254 weakly suppresses
  17. L16:1987 weakly suppresses
  18. L14:630 weakly suppresses
  19. L18:2371 weakly suppresses
  20. L15:1310 weakly suppresses
  21. L14:2025 weakly suppresses
  22. L19:1742 weakly suppresses
  23. L16:2430 weakly excites
  24. L17:683 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 -1.76 and -1.623 values between -1.48 and -1.356 values between -1.35 and -1.2119 values between -1.21 and -1.0828 values between -1.08 and -0.9438 values between -0.94 and -0.8075 values between -0.80 and -0.67144 values between -0.67 and -0.53231 values between -0.53 and -0.39408 values between -0.39 and -0.26623 values between -0.26 and -0.121173 values between -0.12 and 0.01578 values between 0.01 and 0.15224 values between 0.15 and 0.29128 values between 0.29 and 0.4273 values between 0.42 and 0.5653 values between 0.56 and 0.6931 values between 0.69 and 0.8322 values between 0.83 and 0.9715 values between 0.97 and 1.1014 values between 1.10 and 1.248 values between 1.24 and 1.373 values between 1.37 and 1.514 values between 1.51 and 1.652 values between 1.65 and 1.781 values between 1.78 and 1.921 values between 2.60 and 2.741 values between 2.74 and 2.871 values between 3.55 and 3.69offnegativepositiveoften

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. далеко
  2. kennenlernen
  3. orro
  4. люб
  5. psc
  6. getAttribute
  7. mxArray
  8. panion
  9. стал
  10. titleLabel

Suppresses

  1. case
  2. case
  3. (
  4. CAS
  5. G
  6. 当事
  7. 驹
  8. =
  9. #
  10. غر