Neuron Explorer

Qwen3-0.6B

capital M starting a word

A neuron in layer 27 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

Reacts to a capital M that begins a new word or name in the middle of a sentence, such as Migrant, Masa or Magma. Turning it up made the text drift into loosely related passages, with no clear theme.

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

    this simple unleavened flatbread turnover remains a favorite snack of the Mexican and Tex-Mex cuisine.⏎The true quesadilla is made with masa dough. Masa is prepared from maize blanco (white field corn) that is dried and cured

  2. #2 peak

    Present: 30 Years pays tribute to⏎our nationís migrant farmworkers, to the agricultural enterprises that⏎employ them, and to the Geneseo Migrant Centerís 30 years of outreach⏎in service to them.⏎The

  3. #3 peak

    individual and collective), real faces and voices that speak to us in their own words.⏎Sections 8 through 22 tell the story of the Geneseo Migrant Center since its founding in 1968. As the migrant population

  4. #4 peak

    Science | January 13, 2022⏎Bjornevik K, Cortese M, Healy BC, Kuhle J, Mina MJ, Leng Y, Elledge SJ, Niebuhr DW,

  5. #5 peak

    an erupting volcano, showing the process of releasing lava and smoke. Volcanoes erupt because heat within the Earth melts rocks and creates a substance called magma. Magma rises and pushes through the Earths surface and the volcano erupts. Once

  6. #6 peak

    our Patrons Cristina Magistrali, Toren Wallengren, Eric Huffman, Julia Casey, Colton Siefker, Daniel Wenger, Matias Mancini, John Thompson, Chris Krish, and Alvero Wiggins for supporting

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: manyologiesnaynaynaynaynaynaynaynaynaynaynaynaynaynaynaynaynaynaynaynaynaynaynay

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

    talking points and other digital assets to help you market your events and connect to the larger statewide initiative.<|endoftext|>COLUMBIA — A majestic bur oak in mid-Missouri survived the Civil War and floods, but this summer's drought has taken

  2. #2 peak

    that the baby can only see objects about 5cm from the face.⏎Changes occurring in the mother’s body during the 30th week of pregnancy⏎Moms may feel a bit tired on these days, especially if moms are having trouble

  3. #3 peak

    igneous rock classification with magma viscosity, and to connect magma viscosity with volcano explosiveness and morphology.⏎The Grand Canyon⏎Rebecca Teed, Wright State University-Main Campus⏎This interdisciplinary lesson plan deals with the consequences of damming in the

  4. #4 peak

    abolic acidosis, nonketotic hypoglycemia, low or normal total carnitine⏎blood levels, dicarboxylic aciduria.⏎Mild hyperammonemia and slight elevation of liver transaminases may also⏎

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. L22:1138 suppresses
  2. L20:234 suppresses
  3. L24:1190 excites
  4. L17:230 excites
  5. L7:922 suppresses
  6. L1:35 suppresses
  7. L21:505 suppresses
  8. L19:623 excites
  9. L18:553 excites
  10. L18:133 excites
  11. L17:838 excites
  12. L6:13 weakly excites
  13. L18:569 weakly excites
  14. L26:1564 weakly excites
  15. L22:1550 weakly suppresses
  16. L0:73 weakly excites
  17. L13:81 weakly suppresses
  18. L2:1563 weakly excites
  19. L23:206 weakly suppresses
  20. L11:29 weakly excites
  21. L20:151 weakly excites
  22. L18:129 weakly suppresses
  23. L18:750 weakly suppresses
  24. L2:1321 weakly suppresses

Feeds later layers

None: this is the last layer.

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 -52.84 and -47.881 values between -28.00 and -23.042 values between -13.10 and -8.132 values between -8.13 and -3.163889 values between -3.16 and 1.803 values between 1.80 and 6.773 values between 6.77 and 11.742 values between 11.74 and 16.711 values between 26.64 and 31.611 values between 31.61 and 36.581 values between 46.52 and 51.482 values between 140.91 and 145.88offnegativepositiveoften

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. →results
  2. suppose
  3. Entered
  4. 民族
  5. hana
  6. tee
  7. сли
  8. acency
  9. Теп
  10. QUIRE

Suppresses

  1. кра
  2. etta
  3. _PKG
  4. atern
  5. illions
  6. ы
  7. ologies
  8. SS
  9. び
  10. 烦恼