Neuron Explorer

Qwen3-0.6B

"just" as an emphasis word

A neuron in layer 18 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

The neuron fires on the word "just" when it means "exactly" or "simply", as in "just that" or "just how far". It goes negative on nouns like "need" or "possibility" that come before "of". Turning it down or up made the text repeat words like "possibility" and "ability".

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

    skill sets they need to improve.⏎We have spent thousands of hours working with students and developing strategies to help them to succeed on the test. Our track record demonstrates just that. If you are not sure if the

  2. #2 peak

    some similarities between the two have been the source of conflict for thousands of years.⏎Both the Jewish and Muslim faith believe in one God. Being monotheistic means just that, the belief in one God. This is the most obvious similarity between the

  3. #3 peak

    protective equipment, oxygen, and treatments.⏎“Vaccines have never been the way out of this crisis on their own, but this current wave is demonstrating again just what a powerful tool they are to battle back against this virus.⏎“Delta is

  4. #4 peak

    is clear from all that is known of the<|endoftext|>Obese & Fat German Shepherd⏎Like humans, dogs can become obese for several reasons, and the effect is just as severe in them. German Shepherds are prone to becoming obese, and

  5. #5 peak

    she could be both a scientist and mom.⏎Strange to think of a time when women literally weren’t allowed to study. This fact alone definitely makes you grateful for just how far women have come since. When Rubin was elected to the National Academy of

  6. #6 peak

    the cooler climate and higher pH levels on top of Round Mountain in Saluda provide just the right habitat for seeds dropped by migrating birds.⏎“Maybe these birds are def

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: the fact that the presence of the need to have the fact of the fact that to have the fact of the fact that to have the fact of the fact to the fact of the fact of the fact of the fact of the fact of the

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

    06-6214.⏎Atomic Force Microscopy⏎One of the primary issues with electron microscopy techniques for the analysis of aerosol particles lies in the necessity of operating under high vacuum conditions which can fundamentally alter the properties of aerosol particles

  2. #2 peak

    on the environment, and dismissing the impacts that are known. Historically, the US military's reporting of training operations has been patchy - even activists admit the need for some secrecy - but there's reason to think the noncombat environmental impact is

  3. #3 peak

    ° F.⏎- Discuss heat safety precautions with members of your household. Have a plan for wherever you spend time— home, work and school—and prepare for the possibility of power outages.⏎- Check

  4. #4 peak

    Findings suggest that young writers may overlook the possibility that a reader may have a different interpretation, or a false interpretation, even though

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. L17:1605 suppresses
  2. L15:2551 suppresses
  3. L15:802 excites
  4. L16:2948 excites
  5. L15:835 excites
  6. L16:2023 weakly excites
  7. L17:1429 weakly suppresses
  8. L8:645 weakly excites
  9. L17:2107 weakly suppresses
  10. L7:1182 weakly suppresses
  11. L15:2899 weakly suppresses
  12. L15:1450 weakly suppresses
  13. L16:2204 weakly excites
  14. L17:2270 weakly excites
  15. L15:1483 weakly excites
  16. L13:1995 weakly suppresses
  17. L15:2708 weakly suppresses
  18. L7:1923 weakly excites
  19. L11:2719 weakly suppresses
  20. L16:1582 weakly excites 'it' in 'as it sounds' idioms
  21. L6:285 weakly suppresses
  22. L2:12 weakly excites
  23. L16:2419 weakly suppresses
  24. L13:1382 weakly excites

Feeds later layers

  1. L23:914 suppresses
  2. L19:2762 suppresses
  3. L19:2893 suppresses
  4. L21:2749 suppresses
  5. L27:1493 suppresses
  6. L20:233 excites
  7. L20:1539 suppresses
  8. L26:2278 suppresses
  9. L20:1956 suppresses
  10. L25:2373 suppresses
  11. L20:2010 suppresses
  12. L20:2692 suppresses
  13. L20:1560 suppresses
  14. L20:242 excites
  15. L20:2883 suppresses
  16. L19:2070 weakly suppresses
  17. L20:2187 weakly suppresses
  18. L19:1796 weakly suppresses
  19. L21:1441 weakly suppresses
  20. L21:2338 weakly suppresses
  21. L24:480 weakly suppresses
  22. L25:301 weakly suppresses
  23. L27:1199 weakly suppresses
  24. L20:2266 weakly suppresses 'the' before 'idea', 'view' or 'impression'

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.

2 values between -9.96 and -9.541 values between -9.54 and -9.121 values between -7.03 and -6.611 values between -6.19 and -5.771 values between -5.35 and -4.936 values between -4.93 and -4.514 values between -4.51 and -4.092 values between -4.09 and -3.687 values between -3.68 and -3.269 values between -3.26 and -2.8410 values between -2.84 and -2.4217 values between -2.42 and -2.0026 values between -2.00 and -1.5849 values between -1.58 and -1.1668 values between -1.16 and -0.74330 values between -0.74 and -0.322341 values between -0.32 and 0.10791 values between 0.10 and 0.52138 values between 0.52 and 0.9340 values between 0.93 and 1.3515 values between 1.35 and 1.7716 values between 1.77 and 2.1915 values between 2.19 and 2.616 values between 2.61 and 3.035 values between 3.03 and 3.451 values between 3.45 and 3.873 values between 3.87 and 4.291 values between 4.71 and 5.131 values between 5.96 and 6.381 values between 6.38 and 6.80offnegativepositiveoften

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. gregate
  2. ends
  3. itu
  4. reviewed
  5. 형
  6. consumed
  7. реж
  8. -la
  9. carried
  10. (clicked

Suppresses

  1. existence
  2. onacci
  3. jednoc
  4. existence
  5. fact
  6. ationToken
  7. presence
  8. emploi
  9. unsch
  10. необходимости