Neuron Explorer

Qwen3-0.6B

unclear: first letter of a name fragment

A neuron in layer 27 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 reacts to a short first piece of a capitalised name or word, like the O in Oss or the N in Ndebele. The pattern is loose, and turning it up or down only produced repeated, unrelated words.

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

    995 and 2014, World Bank says. Wealth remains unequal, and some countries are falling behind.⏎El Banco Mundial analiza la riqueza de los países, tomando en cuenta no solo el PIB,

  2. #2 peak

    professor and psychologist at NTNU.⏎This research is published in the Journal of Developmental & Behavioral Pediatrics.⏎Previous news in sleep:<|endoftext|>In the Dutch city of Oss, 60 miles southeast of Amsterdam, there's a highway named N

  3. #3 peak

    insurance. About 44% of these people were white, 33% were Hispanic, 15% were black, 5% were Asian/Native Hawaiian or Pacific Islander, and 3% were of another race,

  4. #4 peak

    . In 1787, more than 100 years later, this disaster was described in the historical book "Het Schrickelijcke Oordeel

  5. #5 peak

    a common food source for many Native American tribes including but not limited to the Iroquois, Algonquin, Ojibwa, and Chippewa. It was dried for a winter

  6. #6 peak

    ) and Dashkat Hakaayuʔ “Whitebread” (who told 19% of the stories) https://archive.org/details/traditionsofcadd00dorsrich⏎Explore more about the Caddo history

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: Redaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredaredared

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

    called radius and apply the relevant formula to calculate and return the volume of a sphere based on the given radius.⏎- Your second subroutine should be called getVolumeOfCuboid(), take three parameters called width, length and height and apply the relevant

  2. #2 peak

    certain times, all the digits are⏎consecutive. How many times like this are there between midnight⏎and 7 a.m.?⏎These practical challenges are all about making a 'tray' and covering it with paper.⏎My cousin was

  3. #3 peak

    a liquid brew that is consumed in a ceremonial context.⏎Ayahuasca is made from two plant substances, the woody bark of the vine Banisteriopsis caapi and the leaves of Psychotria viridis. Together, these plant sources

  4. #4 peak

    -Tape measure -Plywood -Circular saw -Ruler or a straight edge -Stapler -Paint or a sealant -Cordless drill -1 inch hole saw -Paintbrush -Safety glasses⏎-

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. L24:346 excites
  2. L24:375 suppresses
  3. L21:160 suppresses
  4. L22:245 weakly suppresses
  5. L23:2981 weakly suppresses
  6. L20:550 weakly excites
  7. L18:1703 weakly excites
  8. L21:237 weakly suppresses
  9. L16:248 weakly excites
  10. L18:569 weakly excites
  11. L20:151 weakly excites
  12. L4:681 weakly suppresses
  13. L23:322 weakly suppresses
  14. L22:530 weakly suppresses
  15. L17:367 weakly excites
  16. L23:268 weakly excites
  17. L18:247 weakly suppresses
  18. L24:105 weakly suppresses
  19. L22:700 weakly suppresses
  20. L0:546 weakly excites
  21. L18:1472 weakly suppresses
  22. L20:1091 weakly suppresses
  23. L8:2470 weakly suppresses
  24. L3:7 weakly excites

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 -25.28 and -23.771 values between -16.23 and -14.721 values between -14.72 and -13.212 values between -13.21 and -11.701 values between -11.70 and -10.202 values between -10.20 and -8.692 values between -8.69 and -7.183 values between -7.18 and -5.675 values between -4.16 and -2.6517 values between -2.65 and -1.143759 values between -1.14 and 0.3789 values between 0.37 and 1.879 values between 1.87 and 3.381 values between 3.38 and 4.892 values between 4.89 and 6.401 values between 6.40 and 7.912 values between 7.91 and 9.422 values between 9.42 and 10.931 values between 10.93 and 12.431 values between 12.43 and 13.942 values between 13.94 and 15.451 values between 15.45 and 16.961 values between 16.96 and 18.471 values between 26.01 and 27.521 values between 33.55 and 35.06offnegativepositiveoften

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. đích
  2. rack
  3. 金字塔
  4. l
  5. iasm
  6. /stdc
  7. r
  8. 找了
  9. behalf
  10. endforeach

Suppresses

  1. ared
  2. 🚩
  3. adamente
  4. mü
  5. .bp
  6. 诸侯
  7. [out
  8. ingly
  9. .LayoutStyle
  10. ney