Neuron Explorer

Qwen3-0.6B

capital V 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

The neuron fires on a capital 'V' that starts a word in the middle of a sentence, like 'Vaping', 'Vihara', or 'Vascular'. Its opposite is a lowercase 'v' starting a word, like 'vases'. Turning it up or down gave text that did not clearly relate to this pattern.

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

    also impair memory and concentration. Nicotine can also affect mood and impulse control.⏎Although vaping may be safer than using cigarettes, there are still potential health risks. Vaping devices are still new and researchers have not been able long-term to examine the

  2. #2 peak

    ⏎In 1993, the foundations to the Dhamma Talaka Peace Pagoda were laid in Birmingham, England. Supported by the Birmingham Buddhist Vihara, the pagoda underwent a large amount of planning. The circumference of

  3. #3 peak

    I. Book I. Blood: The Tissues of Movement, the Vascular Mechanism. Sixth Edition. 10s. 6d.

  4. #4 peak

    Achilles Tendon Tear.⏎Rotator<|endoftext|>When you work with RAID 5 volumes, consider the Requirements for RAID 5 Volumes and Guidelines for RAID 5 Volumes. Many striping guidelines also apply to RAID 5 volume configurations. See

  5. #5 peak

    ated with fat, fibrous and elastic tissue⏎- Increases circulation by pushing blood out of foot⏎What are arteriovenous anastomoses?⏎- Vascular connections in the corium⏎- There are smooth muscles at arterial end;

  6. #6 peak

    are because of early menopause. However, menstruation cycle changes can also occur because of sudden change in lifestyle and lack of nutrition.⏎Less Lubrication Of Vagina⏎A drop in the estrogen levels in the body during menopause may lead

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: why did people person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person person

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

    the life of cut flowers.⏎- Always keep vases and flower containers clean, clean, clean. Bacteria-laden water or

  2. #2 peak

    of the arteries with plaque build up (artherosclerosis), very fast heart rate, very high blood pressure or low heart rate or low blood pressure, drugs causing vaso constriction such as cocaine, smoking, methamphetamine, and

  3. #3 peak

    create problems. Field guides — even excellent new ones like Sibley or National Geographic — show 'standard' individuals. There is excellent literature about the Warbling v. Philadelphia Vireo problem, and more observers should review this literature before claiming

  4. #4 peak

    ing parent. As a result, they might have learned to suppress their anger for fear of retaliation or made a personal vow never to be like their parent.⏎The venter style is at the opposite end of the anger management continuum. Unlike the suppress

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. L22:300 strongly suppresses
  2. L20:336 strongly suppresses
  3. L18:423 suppresses
  4. L23:2815 suppresses
  5. L18:365 excites
  6. L17:765 excites
  7. L2:2142 suppresses
  8. L0:2419 excites
  9. L5:1712 suppresses
  10. L1:18 suppresses
  11. L21:2454 weakly suppresses
  12. L6:13 weakly excites
  13. L10:757 weakly suppresses
  14. L18:778 weakly suppresses
  15. L17:389 weakly excites
  16. L16:95 weakly suppresses
  17. L5:3052 weakly suppresses weighing, counting and measuring
  18. L8:4 weakly excites
  19. L6:12 weakly excites
  20. L19:974 weakly suppresses
  21. L7:421 weakly excites
  22. L1:972 weakly suppresses
  23. L5:2394 weakly excites
  24. L26:1176 weakly excites

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.

2 values between -13.56 and -12.741 values between -11.11 and -10.291 values between -8.66 and -7.843 values between -7.84 and -7.031 values between -7.03 and -6.211 values between -6.21 and -5.402 values between -5.40 and -4.583 values between -4.58 and -3.772 values between -2.95 and -2.137 values between -2.13 and -1.3276 values between -1.32 and -0.503461 values between -0.50 and 0.31335 values between 0.31 and 1.135 values between 1.13 and 1.951 values between 1.95 and 2.761 values between 2.76 and 3.581 values between 3.58 and 4.391 values between 4.39 and 5.211 values between 5.21 and 6.031 values between 10.10 and 10.921 values between 15.82 and 16.631 values between 18.26 and 19.08offnegativepositiveoften

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. 讓他們
  2. setState
  3. ところ
  4. setState
  5. Mixer
  6. ary
  7. State
  8. 几家
  9. .Convert
  10. uD

Suppresses

  1. ega
  2. .self
  3. ik
  4. 基数
  5. doubles
  6. Ử
  7. 配偶
  8. ander
  9. vastly
  10. uples