Neuron Explorer

Qwen3-0.6B

'with' after 'provide us' or 'provided you'

A neuron in layer 9 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

The neuron fires on the word 'with' when it follows phrases like 'provides us with' or 'provided you with'. Its negative side is weak and hard to read. Turning it up gave wandering text that did not clearly relate to providing things.

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

    , hypermilers seek to push their gas tanks to the limit and achieve hypermileage, exceeding EPA ratings for miles per gallon.⏎So, there you have it. How long 'till hyper is replaced by wondermileage or excessiv

  2. #2 peak

    , and provides us with a powerful foundation to ask fundamental questions about the behavior of biological materials.⏎Moreover,

  3. #3 peak

    the chaos destroying the world is to solve a 2,000 year-old mystery: Who is the Cartographer?More⏎We've sent an email with your order details. Order ID #:⏎

  4. #4 peak

    the early Mercury missions beginning in 1961. Today, they observe the Earth from their unique point of view aboard the International Space Station, providing researchers with key data and recording changes over time from human-caused changes like urban growth and

  5. #5 peak

    secrets in the coming months. “This find has the potential to be one of the most significant and exciting archaeological discoveries in the city for many years, providing us with yet more clues as to what life was like in medieval Edinburgh,” he said.⏎

  6. #6 peak

    , they calculate the surface area of the prism. This provides students with the opportunity to work with complex shapes to find surface area in a given context.⏎

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 end. I think about people and places. I have a feeling that it's been (2) minutes. The distance between A and B is 10 cm. When the train passes the station, 30 cm apart,

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

    ). He erected an altar to Zeus in the Temple in Jerusalem, and sacrificed pigs there, which are unclean to Jews. The Maccabee family led

  2. #2 peak

    asted brass buttons in the front, and three brass buttons on each cuff. The shoulders are intricately decorated with epaulets bearing silver oak leaves on a blue field, indicating the Infantry branch of the United States' Army. This type of

  3. #3 peak

    . God gave Moses the Law while Israel wandered in the desert. It was rigid. There was little flexibility in its demands. It declared “an eye for an eye and a tooth for a tooth.”⏎God promised Abraham a son who would be the

  4. #4 peak

    aru Takei, of Osaka Prefecture University in Japan.⏎Whiskers are considered tactile sensors for specific animals like cats, according to the study. Whiskers found on a cat's face for example can help the animal navigate around objects.⏎

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. L2:2568 weakly excites
  2. L6:2457 weakly suppresses
  3. L7:2208 weakly excites
  4. L7:1950 weakly excites
  5. L8:571 weakly excites
  6. L7:1923 weakly excites
  7. L4:411 weakly excites
  8. L3:2533 weakly suppresses
  9. L6:980 weakly suppresses
  10. L8:2463 weakly suppresses
  11. L3:2368 weakly excites
  12. L1:3036 weakly suppresses
  13. L3:699 weakly excites
  14. L4:2558 weakly excites
  15. L8:233 weakly suppresses
  16. L4:334 weakly suppresses
  17. L6:850 weakly excites
  18. L8:2575 weakly excites
  19. L8:2531 weakly excites
  20. L5:459 weakly excites
  21. L6:1303 weakly suppresses
  22. L3:1144 weakly suppresses
  23. L3:1002 weakly suppresses
  24. L7:2712 weakly suppresses

Feeds later layers

  1. L10:886 weakly excites
  2. L24:258 weakly excites
  3. L23:3022 weakly suppresses
  4. L11:2015 weakly excites
  5. L15:1595 weakly suppresses
  6. L19:2956 weakly suppresses
  7. L10:1126 weakly suppresses
  8. L18:604 weakly excites
  9. L18:2419 weakly excites
  10. L18:2117 weakly suppresses
  11. L17:2863 weakly excites
  12. L10:2288 weakly suppresses
  13. L25:1147 weakly suppresses
  14. L17:2009 weakly excites
  15. L22:2537 weakly excites
  16. L20:1908 weakly suppresses
  17. L15:919 weakly excites
  18. L21:1441 weakly excites
  19. L12:273 weakly excites
  20. L12:550 weakly excites
  21. L22:1496 weakly suppresses
  22. L10:1911 weakly suppresses
  23. L17:2956 weakly suppresses
  24. L21:1051 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.

5 values between -0.83 and -0.715 values between -0.71 and -0.5819 values between -0.58 and -0.4635 values between -0.46 and -0.33109 values between -0.33 and -0.21419 values between -0.21 and -0.082189 values between -0.08 and 0.05830 values between 0.05 and 0.17174 values between 0.17 and 0.3052 values between 0.30 and 0.4230 values between 0.42 and 0.559 values between 0.55 and 0.686 values between 0.68 and 0.8013 values between 0.80 and 0.932 values between 0.93 and 1.052 values between 1.18 and 1.302 values between 1.30 and 1.431 values between 1.43 and 1.561 values between 1.93 and 2.063 values between 2.06 and 2.181 values between 2.18 and 2.311 values between 4.07 and 4.20offnegativepositiveoften

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. Churchill
  2. 给
  3. 不足以
  4. 可供
  5. (provider
  6. providing
  7. Patterns
  8. ning
  9. illumin
  10. 多种

Suppresses

  1. schlä
  2. amaño
  3. merg
  4. acked
  5. ić
  6. ��
  7. ibaba
  8. maken
  9. anceled
  10. ersed