Neuron Explorer

Qwen3-0.6B

the word 'wide' in 'a wide range'

A neuron in layer 2 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 fires on the word 'wide' in phrases like 'a wide range of' or 'a wide variety of'. Its negative side is weak and does not show a clear pattern. Turning it up made the model write about many different topics, but not in a way that is clearly tied to the word.

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

    offers a wide variety of Online TEFL Courses and a great number of opportunities for English Teachers and

  2. #2 peak

    able long-term to examine the health effects. Researchers have not been able identify all possible chemicals in ecigarettes.⏎Several studies have shown that vaping can cause a wide range of short-term health problems. You may experience inflammation in your lungs, cough

  3. #3 peak

    diseases is only anticipated to rise as the population ages. The same is valid internationally and increasingly in emerging nations.⏎These trends have sparked a wide range of global, national, state, and local initiatives, as well as in

  4. #4 peak

    , such as factories, may also be at risk of exposure to rat killers, slug pellets, ant killers and weed killers.⏎Pesticide poisoning can present a wide variety of symptoms, depending on both the type of pesticide that a person is exposed

  5. #5 peak

    7 to Year 10, but preferably in Years 7 or 8.⏎In Years 11 and 12, NSW schools offer a wide variety of languages, catering for beginning students to background speakers.⏎Our Faculty Members⏎

  6. #6 peak

    Great Lakes water quality, rapid reduction in ice cover and the resurgence of some pollutants like excess nutrients are among the indicators currently raising concerns. Based on contributions from a wide range of U.S. and Canadian experts, the report reveals a

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 feel like I'm trying to be a part of the world. I'm trying to be a part of... what I'm. I feel like I'm trying to be... I feel like I'm trying to be... I feel like

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

    , adaptable, and easily taught.⏎“The social relationships [between] these things matter a lot. And these things have got to be created, developed

  2. #2 peak

    lateral sclerosis (ALS) and Huntington’s disease, but don’t always activate the right proteins at the right time, a recent study shows.⏎“[The cells] do not always realize there is a problem, or know how to solve it,

  3. #3 peak

    of meteor surveillance cameras to determine the fireball's trajectory, denoted by the black arrow in the map below:⏎"The asteroid entered at a [relatively slow] speed

  4. #4 peak

    pes simplex virus] and other pathogens," the researches wrote in their report. "Circum

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. L1:1833 weakly excites
  2. L1:809 weakly suppresses
  3. L1:1478 weakly excites
  4. L0:933 weakly excites
  5. L1:222 weakly excites
  6. L0:175 weakly suppresses
  7. L0:2813 weakly suppresses
  8. L0:385 weakly excites
  9. L1:1971 weakly suppresses
  10. L1:175 weakly excites
  11. L0:834 weakly suppresses
  12. L0:201 weakly suppresses
  13. L0:2067 weakly suppresses
  14. L1:1016 weakly excites
  15. L0:2349 weakly excites
  16. L0:1661 weakly suppresses
  17. L0:2216 weakly excites
  18. L1:130 weakly excites
  19. L0:877 weakly excites
  20. L0:2543 weakly excites
  21. L0:376 weakly excites
  22. L0:92 weakly suppresses
  23. L0:1847 weakly suppresses
  24. L0:2669 weakly excites

Feeds later layers

  1. L15:1667 weakly excites
  2. L21:2058 weakly suppresses
  3. L8:1112 weakly suppresses
  4. L25:1161 weakly excites
  5. L15:936 weakly excites
  6. L8:2346 weakly suppresses
  7. L6:1043 weakly suppresses
  8. L27:307 weakly suppresses
  9. L4:2132 weakly suppresses
  10. L5:1086 weakly suppresses
  11. L11:1683 weakly excites
  12. L15:257 weakly suppresses
  13. L15:2373 weakly excites
  14. L20:1352 weakly excites
  15. L17:1268 weakly suppresses
  16. L22:2756 weakly suppresses
  17. L25:1760 weakly suppresses
  18. L9:1182 weakly suppresses
  19. L6:939 weakly excites
  20. L13:787 weakly suppresses
  21. L13:1516 weakly suppresses
  22. L22:85 weakly suppresses
  23. L19:2907 weakly excites comma right after 'and' in lists
  24. L9:2283 weakly suppresses

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 -2.05 and -1.961 values between -1.53 and -1.441 values between -1.19 and -1.101 values between -1.10 and -1.012 values between -0.84 and -0.761 values between -0.76 and -0.671 values between -0.58 and -0.504 values between -0.50 and -0.415 values between -0.41 and -0.3337 values between -0.33 and -0.24154 values between -0.24 and -0.15604 values between -0.15 and -0.071911 values between -0.07 and 0.02843 values between 0.02 and 0.11217 values between 0.11 and 0.1973 values between 0.19 and 0.2820 values between 0.28 and 0.3612 values between 0.36 and 0.4510 values between 0.45 and 0.544 values between 0.54 and 0.622 values between 0.62 and 0.711 values between 0.79 and 0.882 values between 1.14 and 1.221 values between 1.31 and 1.40offnegativepositiveoften

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. firstname
  2. accord
  3. represented
  4. ouncill
  5. need
  6. .Display
  7. Needs
  8. destruct
  9. 化进程
  10. acceptable

Suppresses

  1. ler
  2. kicked
  3. RESS
  4. onyms
  5. lers
  6. inois
  7. ellen
  8. emen
  9. gens
  10. ression