Neuron Explorer

Qwen3-0.6B

'because' after a claim

A neuron in layer 0 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 'because' when it comes right after a statement and introduces the reason for it. Turning it up made the model's text drift into general, unrelated wording, so the steering did not reveal 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

    ists. They use modern conservation practices to protect our nation's water supplies. Many times these efforts are put in place voluntarily because farmers are driven by a strong stewardship ethic.⏎However, the restoration bill largely

  2. #2 peak

    month chosen because of a widely believed tradition that the world was created in March, and November is

  3. #3 peak

    about the fate of your tree, carefully look at the extent of the damage and assess the overall health of the tree.⏎“It could be that the tree was damaged because it’s diseased, weak or on its way out anyway,” Trinklein

  4. #4 peak

    -rap had an intellectual bent because of accessibility of education which was promoted by policies like the affirmative action, it’s

  5. #5 peak

    Mechanical strength is critical because the shell protects the instruments inside against mechanical shock. Enclosures for on-whale

  6. #6 peak

    are vital because they help train kids for a new frontier of jobs, Insight Communications Director of Communications

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 been reading this for a long time, I have been thinking about it. I have been thinking about it. I have been thinking about it. I have been thinking about it. I have been thinking about it. I have been

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

    ottled if you turn the rotating stage|⏎|Tourmal<|endoftext|>The Catechism of the Catholic Church states:⏎"Every act of war directed to the indiscriminate destruction of whole cities or vast areas with their inhabitants is a crime against God

  2. #2 peak

    of urgency for a patient’s ocular findings such as visual field defects, cranial neuropathies, double vision, optic neuropathy, ptosis, pupillary abnormalities and loss of vision.⏎How long does it take for vision therapy to work

  3. #3 peak

    ”在汉语中具有较大的作用,使用率高,但是泰国学生经常在学习和使用汉语助动词中产生各种的偏误。本文通过调查法、统计

  4. #4 peak

    't have family or friends to turn to.⏎Barack Obama the president of the United States has a plan.'⏎The people described above are America's homeless.These unfortunate individuals often we see living on the streets in the downtown areas of our

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

None: this is the first layer.

Feeds later layers

  1. L10:851 weakly excites
  2. L9:1002 weakly suppresses comma after who, when or where
  3. L6:313 weakly suppresses
  4. L23:706 weakly suppresses
  5. L18:2010 weakly suppresses
  6. L22:258 weakly suppresses
  7. L21:1336 weakly suppresses
  8. L10:571 weakly excites
  9. L25:1205 weakly suppresses
  10. L4:3039 weakly suppresses
  11. L7:2934 weakly suppresses
  12. L5:2009 weakly suppresses
  13. L7:1877 weakly suppresses
  14. L18:2890 weakly excites
  15. L18:1785 weakly suppresses
  16. L3:640 weakly excites
  17. L6:665 weakly excites
  18. L21:1605 weakly suppresses
  19. L6:178 weakly excites
  20. L22:627 weakly suppresses
  21. L26:2935 weakly suppresses
  22. L21:821 weakly excites
  23. L5:940 weakly excites
  24. L7:379 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 -0.44 and -0.371 values between -0.37 and -0.313 values between -0.31 and -0.2527 values between -0.25 and -0.18106 values between -0.18 and -0.12571 values between -0.12 and -0.061883 values between -0.06 and 0.01970 values between 0.01 and 0.07202 values between 0.07 and 0.1349 values between 0.13 and 0.1921 values between 0.19 and 0.2611 values between 0.26 and 0.3214 values between 0.32 and 0.386 values between 0.38 and 0.456 values between 0.45 and 0.5111 values between 0.51 and 0.573 values between 0.57 and 0.631 values between 0.63 and 0.702 values between 0.70 and 0.761 values between 0.76 and 0.825 values between 0.82 and 0.891 values between 0.89 and 0.951 values between 1.01 and 1.082 values between 1.14 and 1.202 values between 1.20 and 1.261 values between 1.26 and 1.331 values between 1.33 and 1.392 values between 1.45 and 1.521 values between 1.52 and 1.581 values between 1.58 and 1.641 values between 1.64 and 1.701 values between 2.02 and 2.08offnegativepositiveoften

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. nes
  2. nowhere
  3. tering
  4. ippo
  5. Associates
  6. luk
  7. NES
  8. never
  9. lee
  10. PROP

Suppresses

  1. ;br
  2. 矾
  3. щит
  4. 雨水
  5. izr
  6. 节
  7. 即可
  8. 时节
  9. 我可以
  10. elize