Neuron Explorer

Qwen3-0.6B

first person 'I' or 'my' in speech

A neuron in layer 8 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on the word 'I' or 'my' when a person is speaking or writing about themselves, especially inside quotes. It is one of the strongest neurons we looked at. Turning it up did not make the writing clearly first person, though.

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

    picture of.⏎"God," he said.⏎"Why Johnny," she said, "you can't do thatbecause nobody knows what God looks like."⏎"They will when I'm finished," he assured her.⏎That story presents concretely, almost blatantly

  2. #2 peak

    2019, the station will operate on renewable natural gas (RNG) produced as a byproduct of wastewater treatment.⏎“Our future is green, and I’m very proud that we’re bringing the first natural gas vehicles to the City’s

  3. #3 peak

    Department and Flint Hills Resources.⏎“The state’s response teams responded pretty quickly," said Newstead. "I don’t know exactly how much, they put thousands and thousands of feet of absorb

  4. #4 peak

    10."⏎Others welcome the report. "The estimate is transparent and conservative," says particle physicist Georg Weiglein at the University of Durham, UK. "I ...<|endoftext|>The Diary of Anne Frank Essay written by l

  5. #5 peak

    and game play.⏎The app is available to download for free.⏎or visit myspira.com to download the app<|endoftext|>Section 8: The Church⏎Week

  6. #6 peak

    the IDE as well as more adept at program creation.⏎Go no further if you're looking for the course that will guide you into the world of programming! With my course I can guarantee that the knowledge you learn will help

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: climate change and the increase of the average temperature, which is 2 degrees for the purpose of designing a strategic plan. But there is a need to ensure the quality of a strategic plan. Now, we have a dynamic, flexible, and

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

    and create models to explore how neural circuits are organized, and how they give rise to behaviour and cognition — among the deepest mysteries in neuroscience. Ultimately, said Markram, the HBP would even help researchers to grapple with disorders such as Alzheimer

  2. #2 peak

    not land a steady job. A handful of boys from up and down Senegal’s coast. The captain, Mamour Ndiaye, who always goes to sea wearing the same tank top in the pattern of the

  3. #3 peak

    44 g for France. France has no<|endoftext|>Lynne from Tennessee writes:⏎I’m trying to learn Windows 8.1 and it is really confusing me. Can you explain what: an App is and do I really need it?

  4. #4 peak

    ulators with ideas and advice to solve formulating challenges. To submit a question, e-mail FormulateThis@allured.com.⏎Question: I’m trying to understand cosmetic emulsion inversion. What actually happens inside the emulsion at the phase borders

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. L5:52 strongly suppresses
  2. L6:200 strongly excites
  3. L7:1034 strongly excites
  4. L5:771 strongly suppresses
  5. L7:834 excites
  6. L4:1855 excites
  7. L1:1063 excites
  8. L5:1028 suppresses
  9. L7:1412 excites
  10. L7:555 suppresses
  11. L6:214 suppresses
  12. L4:1268 suppresses
  13. L7:2429 suppresses
  14. L6:410 weakly suppresses
  15. L6:1140 weakly excites
  16. L4:832 weakly excites
  17. L4:1477 weakly excites
  18. L7:169 weakly suppresses
  19. L0:1833 weakly suppresses
  20. L2:853 weakly excites
  21. L4:499 weakly suppresses
  22. L7:1004 weakly excites
  23. L7:67 weakly excites
  24. L5:151 weakly excites

Feeds later layers

  1. L20:1058 suppresses
  2. L11:1002 excites
  3. L18:1025 suppresses
  4. L19:2124 excites
  5. L17:2086 excites
  6. L11:1844 excites
  7. L12:1662 excites
  8. L9:919 excites
  9. L22:1065 excites
  10. L16:2810 suppresses
  11. L9:652 suppresses
  12. L25:2082 excites first-person 'I' starting a clause
  13. L10:419 excites
  14. L13:2559 excites
  15. L20:1110 suppresses
  16. L11:1741 excites
  17. L25:1541 excites
  18. L10:2693 excites
  19. L10:2504 weakly excites
  20. L9:885 weakly suppresses research and study wording
  21. L11:2798 weakly suppresses
  22. L10:1679 weakly suppresses
  23. L16:3065 weakly excites
  24. L24:1134 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 -3.09 and -2.841 values between -2.32 and -2.061 values between -2.06 and -1.801 values between -1.80 and -1.545 values between -1.28 and -1.034 values between -1.03 and -0.7745 values between -0.77 and -0.511106 values between -0.51 and -0.252325 values between -0.25 and 0.01314 values between 0.01 and 0.2739 values between 0.27 and 0.5326 values between 0.53 and 0.7810 values between 0.78 and 1.049 values between 1.04 and 1.302 values between 1.30 and 1.562 values between 1.56 and 1.821 values between 1.82 and 2.084 values between 2.08 and 2.343 values between 2.34 and 2.591 values between 2.59 and 2.851 values between 3.11 and 3.373 values between 3.37 and 3.631 values between 4.14 and 4.401 values between 5.18 and 5.441 values between 6.99 and 7.25offnegativepositiveoften

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. 妻子
  2. 老婆
  3. 我就
  4. ible
  5. ificate
  6. assignments
  7. ivant
  8. esposa
  9. 建议
  10. 我自己

Suppresses

  1. .Scan
  2. eds
  3. elkaar
  4. dq
  5. _exam
  6. strerror
  7. ແ
  8. matter
  9. 鲷
  10. -Fi