Neuron Explorer

Qwen3-0.6B

lowercase p 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

This neuron reacts to the letter p when it begins a word, such as pumpkin, pox or peregrine. Turning it up made the model's writing repeat words and drift, so the steering does not show a 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

    lutein, and zeaxanthin – good for your eyes, skin, immune system, and general health.⏎Consider making your next smoothie a “pumpkin pie” smoothie! Place the following in a blender:⏎•

  2. #2 peak

    arm around Little Man." (Mildred D. Taylor, _Roll of Thunder, Hear My Cry_)⏎- Are you a word wiz?⏎The "pamper"

  3. #3 peak

    - Hernias: Hernia is the popular term for a series of different diagnoses, all identified by outpouchings on the ventral aspect of the abdominal wall of pigs. Hernias

  4. #4 peak

    pox is Kyuta and thicken chicken pox.⏎How to make chickenpox⏎What is chicken pox⏎Chicken Pox in Hindi means chickenpox, which is an infectious disease spread by a virus called varicella z

  5. #5 peak

    12 import random verb = ['erratic', 'unbelievable', 'unfortunate', 'inconsequential'] fruit = ['raspberry', 'pomegranite', 'bananana', 'grape', 'loganberry

  6. #6 peak

    to Norway and Sweden, although the Lokke-name has been abandoned and the plants are called “trollhavre” (troll oat) and “pukhagre”.⏎On the other hand, when Lokke, on

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: suppose there are two spectrophotroscopically spectrophotosanathos spectrophotosanathos spectrophotosanathos spectrophotosanathos spectrophotosanathos spectroph

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

    Mode.com. Retrieved 05, 2012, from http://www.studymode.com/essays/The-Struggle-For-Power-In-The-994323.html⏎"The Struggle for

  2. #2 peak

    2014|⏎|ISBN: ||9781312744967 (DRM-EPUB)|⏎|Read Aloud: ||not allowed|<|endoftext|>In 1

  3. #3 peak

    diapers to landfills are being used to generate alternative sources of power that run equipment, vehicles and buildings around the world!⏎Confiscated Booze Converted into Bus-Powering Biogas: nearly 200,000 gallons of

  4. #4 peak

    /essays/The-Struggle-For-Power-In-The-994323.html>.⏎"The Struggle for

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. L23:1099 excites
  2. L18:196 suppresses
  3. L20:648 suppresses
  4. L19:884 suppresses
  5. L17:214 excites
  6. L22:428 excites
  7. L22:979 excites
  8. L22:1780 excites
  9. L2:1554 excites
  10. L1:6 suppresses
  11. L21:571 suppresses
  12. L19:89 excites
  13. L26:1564 excites
  14. L20:322 suppresses
  15. L8:14 excites
  16. L0:498 excites
  17. L6:875 suppresses
  18. L16:353 weakly suppresses
  19. L24:938 weakly suppresses
  20. L18:569 weakly excites
  21. L6:12 weakly excites
  22. L20:2984 weakly excites
  23. L6:13 weakly excites
  24. L2:202 weakly excites "of" after "many" or "which"

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 -36.91 and -31.633070 values between -5.25 and 0.02836 values between 0.02 and 5.301 values between 168.85 and 174.13offnegativepositiveoften

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. 躬
  2. nier
  3. getField
  4. 目前已
  5. тогда
  6. ฤษ
  7. Hiện
  8. 现
  9. ようです
  10. 闷

Suppresses

  1. aths
  2. ages
  3. ath
  4. hone
  5. rob
  6. arro
  7. ython
  8. ará
  9. rec
  10. oints