Neuron Explorer

Qwen3-0.6B

parenthesis after prophet or Allah names

A neuron in layer 11 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 opening bracket that follows honorific names, like 'Allah (swt)' or 'the Prophet (peace be upon him)'. Those are mostly in Islamic religious writing. Steering did not show a clear theme.

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

    certainly supports our point of view that in the grief of a departure, wailing is a natural habit. Wailing or weeping is a natural instinct hence Allah (swt) has

  2. #2 peak

    2:228)⏎Through the beautiful discourse of the Holy Quran and Sunnah, Muslims come to learn about the various rights that Allah (SWT) has enjoined upon His creation – in a practical and detailed manner

  3. #3 peak

    another act of worship is regarded as general du’aa’; in this case there is nothing wrong with raising the hands. It was narrated that the Prophet (peace and blessings of Allaah be upon him) spoke of a man who raised

  4. #4 peak

    the Holy Prophet (upon whom be peace) and its object to remove his anxiety and distress, which

  5. #5 peak

    وان مقاله [English]⏎نویسنده [English]چکیده [English]⏎The author in this article has chosen all Imam Ali’s (A.S) speeches in Nahj-Albalagheh which are specifically about

  6. #6 peak

    things, Allah (SWT) has made men the protectors and guardians of women – it is

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 need for a plan. I need to get the people I know, the ones who are in a business, maybe the finance, the people who have a small business, maybe a home, maybe a home, maybe a home, 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

    into the mix. Excitingly, these histones, when expressed in E. coli, bind the genome nearly<|endoftext|>Definition of Nupe in English:⏎noun (plural same or Nupes)⏎2 [mass noun] The Benue-C

  2. #2 peak

    review worksheet, students are given sentences and must find the mistake. Students correct the mistakes when they find them using their knowledge of verb tense.⏎3 Views 28 Downloads<|endoftext|>Blank Electoral College Map 201

  3. #3 peak

    15(2):57-61 DOI:http://dx.doi.org/10.4314/aas.v15i2.5⏎© 2018 Author. This work is licensed under the

  4. #4 peak

    systems.⏎What is Lyra's demon?⏎lyra's demon, pantalaimon /ˌpæntəˈlaɪmən/, is his most beloved companion, whom he calls “

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. L10:1785 suppresses
  2. L10:252 excites
  3. L10:510 excites
  4. L10:500 excites
  5. L8:1728 suppresses
  6. L10:1632 suppresses
  7. L8:790 excites
  8. L9:1593 excites
  9. L10:1706 weakly suppresses
  10. L8:756 weakly suppresses
  11. L10:2810 weakly suppresses
  12. L9:776 weakly suppresses
  13. L9:2057 weakly excites
  14. L1:1817 weakly excites
  15. L8:251 weakly suppresses
  16. L10:1043 weakly suppresses
  17. L9:308 weakly excites
  18. L10:1013 weakly suppresses
  19. L4:953 weakly suppresses
  20. L10:2036 weakly suppresses
  21. L7:2038 weakly excites
  22. L7:575 weakly suppresses
  23. L10:976 weakly excites
  24. L9:3010 weakly suppresses

Feeds later layers

  1. L15:943 excites
  2. L15:988 excites
  3. L12:1598 excites
  4. L17:2354 excites
  5. L12:2700 excites
  6. L13:1522 excites
  7. L13:283 excites
  8. L13:8 suppresses
  9. L12:120 suppresses
  10. L12:787 excites
  11. L13:2352 excites
  12. L13:1900 excites
  13. L14:666 suppresses
  14. L13:1748 weakly excites
  15. L15:420 weakly excites
  16. L12:1826 weakly excites
  17. L15:30 weakly excites
  18. L14:2032 weakly excites
  19. L12:507 weakly excites
  20. L13:2450 weakly excites
  21. L13:2847 weakly excites
  22. L13:1167 weakly excites
  23. L16:1226 weakly excites
  24. L17:2402 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 -1.91 and -1.811 values between -1.42 and -1.322 values between -1.32 and -1.221 values between -1.12 and -1.032 values between -1.03 and -0.931 values between -0.93 and -0.835 values between -0.83 and -0.733 values between -0.73 and -0.634 values between -0.63 and -0.5421 values between -0.54 and -0.4484 values between -0.44 and -0.34256 values between -0.34 and -0.24582 values between -0.24 and -0.14989 values between -0.14 and -0.041347 values between -0.04 and 0.05377 values between 0.05 and 0.15121 values between 0.15 and 0.2552 values between 0.25 and 0.3521 values between 0.35 and 0.4512 values between 0.45 and 0.558 values between 0.55 and 0.647 values between 0.64 and 0.742 values between 0.74 and 0.841 values between 0.84 and 0.941 values between 0.94 and 1.043 values between 1.04 and 1.132 values between 1.23 and 1.332 values between 1.92 and 2.02offnegativepositiveoften

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. tử
  2. esse
  3. esser
  4. سابق
  5. _stderr
  6. orget
  7. costa
  8. Administrator
  9. 謝
  10. essen

Suppresses

  1. ICENSE
  2. GEST
  3. .Line
  4. built
  5. -'
  6. onden
  7. ıyor
  8. very
  9. easily
  10. 深层