Neuron Explorer

Qwen3-0.6B

'with' after provide or familiarize

A neuron in layer 4 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 reacts to the word 'with' when it follows verbs like provide, familiarize or 'what could be wrong', where a thing is being given or connected to someone. Turning it up made the writing drift into vague, general phrasing.

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

    are very nearly opposite.⏎In his book The Schools Our Children Deserve, Alfie Kohn adds:⏎What could possibly be wrong with results? To answer this question, we first have to recognize that for people to

  2. #2 peak

    is an issue, and what could be wrong with being an "insider." Some of the papers discuss the issue of objectivity

  3. #3 peak

    the United States, Canada, Greenland, Russia, Norway, Sweden, and Finland. Researchers hope the study results will provide Native organizations and local governments across the Arctic with information to help make policy decisions. As a major step toward that goal, the

  4. #4 peak

    is looking at how wind changes or rain could affect the spread of nuclear materials in Japan.⏎"(The center) has been activated to provide the U.S. government with a predictive modeling capability to analyze a variety of potential situations," LaVera said

  5. #5 peak

    rules include the following:⏎Follow Standardized Symbols - You likely won't get very far trying to read a circuit diagram without familiarizing yourself with the various symbols and their meanings. Different components are usually represented by specific symbols.

  6. #6 peak

    applied in the clinical setting to help avoid drug calculation and administration errors is boxed throughout the text.⏎- Full-color illustrations, photographs, and drug labels familiarize you with what you'll encounter in the clinical setting.⏎- Current recommendations from The Joint Commission

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 book "A Little Help, a Little Love" (A.L.H.) by Mary R. and her friends. We've been our team, we are, and we're, and we're, and with our team, we are

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

    ), invented the tactic, and became the first driver to win with it, in the second Daytona 500, in 196

  2. #2 peak

    018 Chicago Botanic Garden and my.chicagobotanic.org<|endoftext|>Hello. Sign In⏎Please enter a valid city, state or zip code⏎With the Food and Drug Administration (FDA) announcing efforts to reduce salt in the foods

  3. #3 peak

    47:3; Nahum 3:2; etc.⏎He [God] caused their chariot wheels to swerve, and He made them drive with difficulty; so the Egyptians each said, “Let me flee from Israel, for

  4. #4 peak

    had a C-section were less likely to do pelvic floor exercises, probably because they didn’t push the baby out with the pelvic floor. But pregnancy itself that affects the pelvic floor, so pelvic floor

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. L2:863 suppresses
  2. L3:1218 suppresses
  3. L3:1968 excites
  4. L0:2342 suppresses
  5. L3:187 excites
  6. L3:2170 excites
  7. L3:421 suppresses
  8. L2:2328 weakly suppresses
  9. L3:272 weakly excites
  10. L3:186 weakly suppresses
  11. L3:464 weakly excites
  12. L3:929 weakly excites
  13. L2:49 weakly suppresses
  14. L3:1041 weakly excites
  15. L3:2277 weakly excites
  16. L3:691 weakly excites
  17. L3:189 weakly excites
  18. L2:237 weakly excites
  19. L1:2268 weakly excites
  20. L3:50 weakly excites
  21. L0:1224 weakly suppresses
  22. L3:1568 weakly suppresses
  23. L0:2347 weakly suppresses
  24. L2:41 weakly suppresses

Feeds later layers

  1. L9:1856 strongly suppresses "with" after a noun, introducing contents
  2. L19:2018 suppresses
  3. L17:2363 suppresses
  4. L5:910 suppresses
  5. L9:1340 suppresses
  6. L16:1860 suppresses
  7. L6:846 suppresses
  8. L5:763 suppresses
  9. L8:2632 suppresses
  10. L6:2543 suppresses
  11. L9:2150 suppresses
  12. L21:1060 suppresses
  13. L16:2307 suppresses
  14. L11:1578 suppresses
  15. L16:1750 suppresses
  16. L15:2682 suppresses
  17. L17:303 suppresses
  18. L10:886 weakly suppresses
  19. L16:2564 weakly suppresses
  20. L9:2267 weakly suppresses 'with' after exchange nouns
  21. L14:1478 weakly suppresses
  22. L23:3038 weakly excites
  23. L7:2087 weakly suppresses
  24. L18:2087 weakly suppresses "with" after a group noun

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 -9.14 and -8.901 values between -7.17 and -6.933 values between -5.70 and -5.453 values between -3.73 and -3.492 values between -3.24 and -3.001 values between -3.00 and -2.752 values between -2.01 and -1.772 values between -1.52 and -1.281 values between -1.03 and -0.781 values between -0.78 and -0.546 values between -0.54 and -0.29149 values between -0.29 and -0.053195 values between -0.05 and 0.20509 values between 0.20 and 0.4532 values between 0.45 and 0.69offnegativepositiveoften

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. chemist
  2. CCA
  3. �
  4. ölü
  5. 很好
  6. 请输入
  7. ASIC
  8. cies
  9. pla
  10. 先是

Suppresses

  1. regards
  2. regard
  3. lasses
  4. tones
  5. prise
  6. respect
  7. Confidence
  8. Coul
  9. having
  10. USTER