Neuron Explorer

Qwen3-0.6B

the word 'gene' and relatives

A neuron in layer 4 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 lights up on the word 'gene' and words built from it, such as 'genealogy' and 'genetic'. It is a clear topic detector, but turning it up or down did not change the text in an obvious, meaningful way.

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

    ius' genealogy began in 1996 and is the fifth of its kind.

  2. #2 peak

    about how your disease will progress and more information about the risk of eye disease for other members of your family. Knowing the gene that causes your eye disease may also be required to be eligible for some types of

  3. #3 peak

    “pure” version of the diet.⏎Few published studies evaluate risks and benefits of a raw food<|endoftext|>Females descendants of Confucius will be included in the genealogy now being compiled.⏎The current project to trace Confuc

  4. #4 peak

    6, corn containing a gene that allows it to create a protein that is toxic to certain insects, yet safe

  5. #5 peak

    get a mutation test done,” said Axelrod. “This is important knowledge for his family to have, especially if he has kids.” She said that a positive gene mutation test also increases the chances of getting prostate and pancreatic cancer.⏎A family history

  6. #6 peak

    a gene being made. Those duplicates can be passed along to subsequent generations and, on very

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: I have a 3D object, and I have a 2D object. What is the result of this? The answer to the question is that, and the object has a 3D object. I need to make sure that

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

    bodies of water, sometimes in small groups called a waterspout cluster or family. Unlike tornadoes over land that often become visible due to the dust and debris present within them, a waterspout is made up of swirling droplets of water

  2. #2 peak

    determining, and to appreciate the ever-present urgency to engage these problems and develop ethical and effective ways to restore and sustain the

  3. #3 peak

    in other words they are actually involved in the dispute that appears before them; or having a pecuniary or proprietary interest in the outcome of the decision, which means they stand to lose or gain (power, influence, money or other

  4. #4 peak

    of the Central Pacific and the governor of California, deposited the first shovelful of dirt for the railroad’s embankment …”⏎Designs were in place for the Sacramento shops by 1867 and two years later, by

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. L3:159 excites
  2. L3:615 excites
  3. L3:249 suppresses
  4. L3:805 weakly excites
  5. L1:2708 weakly suppresses
  6. L3:1408 weakly excites
  7. L2:1862 weakly excites
  8. L3:1176 weakly suppresses
  9. L1:1198 weakly suppresses
  10. L3:113 weakly suppresses
  11. L3:691 weakly excites
  12. L0:1604 weakly suppresses
  13. L2:2789 weakly excites
  14. L3:995 weakly suppresses
  15. L1:1630 weakly excites
  16. L1:1971 weakly suppresses
  17. L1:431 weakly suppresses
  18. L2:2934 weakly excites
  19. L3:2197 weakly excites
  20. L2:2649 weakly suppresses
  21. L2:1026 weakly suppresses
  22. L1:169 weakly suppresses
  23. L3:1141 weakly suppresses
  24. L1:1670 weakly excites

Feeds later layers

  1. L8:423 excites
  2. L5:667 excites
  3. L25:2750 suppresses
  4. L11:173 excites
  5. L5:10 excites
  6. L8:852 excites comma inside large numbers
  7. L16:592 weakly excites
  8. L18:708 weakly excites
  9. L16:414 weakly excites
  10. L25:1030 weakly excites
  11. L17:259 weakly excites
  12. L23:883 weakly suppresses
  13. L21:1905 weakly suppresses
  14. L7:116 weakly excites
  15. L18:309 weakly suppresses
  16. L20:2979 weakly suppresses
  17. L17:2009 weakly suppresses
  18. L24:1998 weakly suppresses
  19. L9:2231 weakly excites
  20. L22:1515 weakly suppresses
  21. L26:2939 weakly excites
  22. L11:611 weakly suppresses
  23. L22:1970 weakly suppresses
  24. L12:2575 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 -1.80 and -1.691 values between -1.59 and -1.481 values between -1.28 and -1.172 values between -1.17 and -1.073 values between -0.96 and -0.868 values between -0.86 and -0.7612 values between -0.76 and -0.6515 values between -0.65 and -0.5518 values between -0.55 and -0.4422 values between -0.44 and -0.3491 values between -0.34 and -0.24226 values between -0.24 and -0.13761 values between -0.13 and -0.031959 values between -0.03 and 0.08510 values between 0.08 and 0.18151 values between 0.18 and 0.2857 values between 0.28 and 0.3931 values between 0.39 and 0.4913 values between 0.49 and 0.609 values between 0.60 and 0.702 values between 0.70 and 0.803 values between 0.80 and 0.913 values between 0.91 and 1.011 values between 1.01 and 1.124 values between 1.12 and 1.221 values between 1.22 and 1.321 values between 1.32 and 1.431 values between 2.05 and 2.161 values between 2.26 and 2.36offnegativepositiveoften

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. akter
  2. Investigators
  3. estation
  4. 킷
  5. erculosis
  6. Preference
  7. ulatory
  8. fare
  9. iscing
  10. ница

Suppresses

  1. ése
  2. öt
  3. dead
  4. 对他们
  5. grav
  6. +Sans
  7. sizes
  8. 擒
  9. xpath
  10. deduct