Neuron Explorer

Qwen3-0.6B

'about' in 'it's not about' phrasing

A neuron in layer 1 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 'about' in phrases like 'it's all about', 'it's not just about' or 'it isn't about', where the writer says what something is really concerned with. Turning it up did not clearly change the model's output.

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

    become apparent. It allows you to evaluate your behavior with food, which can help you identify changes that you can make to implement a healthier lifestyle.⏎It’s all about listening to your body’s cues. This allows you to realize when you’re hungry

  2. #2 peak

    and environmentally responsible use of Information Technology resources within an organization. It is not just about reducing the corporate carbon footprint; the goal of Green IT is also to significantly reduce

  3. #3 peak

    ’m talking about is helping kids apply knowledge, think critically, imagine, be creative, be confident about being lifelong learners. It’s not simply about memorising facts and being able to recite that which one has memorised;

  4. #4 peak

    the current is bringing something, it’s all about experiences. Nature is everywhere. Birds, fish, animals and all kinds of trees and plants. It’s all about direction and distance and no choice is wrong.<|endoftext|>Prognosis and survival for

  5. #5 peak

    Health Disparities workgroup of Facing Race = Embracing Equity (FR=EE) is working to improve the doctor-patient relationship.⏎"It's not about, 'You're racist,' " said Candice Lucas, director of Community Health

  6. #6 peak

    : French History: Biographies<|endoftext|>White balance isn’t about the color of the sun – it’s about the color of the light. The

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 working on this problem, and I am not sure of the answer. So I need to think about it again. I need to think about it again. So I have been thinking about this problem, and I am not sure

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

    and Denmark offered him large honorary pensions which he modestly declined. At the urging of fellow scientists he attempted to form an imperial academy of science, but was thwarted by political enemies of the Jesuits. He did succeed in publishing a very timely

  2. #2 peak

    his compatriot Sutan Sjahrir sought to join forces with other nationalist leaders, including Sukarno. The organizational efforts of these men were thwarted by the repressive policies of the colonial state. First Sukarno was arrested

  3. #3 peak

    bigger killer: infectious disease.⏎"When a child is diagnosed, parents ask: Why is this in our genes?" said Butte, assistant professor of pediatric cancer biology and a bio

  4. #4 peak

    to distinguish themselves as cancer stem cells. In the K-RAS model, all tumor cells were equally likely to propagate tumors<|endoftext|>Pharmacists are caring for more individuals of diverse age, gender, race, ethnicity, socioeconomic status,

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. L0:918 weakly excites
  2. L0:558 weakly suppresses inside all-caps abbreviations
  3. L0:315 weakly suppresses
  4. L0:3068 weakly excites
  5. L0:559 weakly suppresses
  6. L0:1045 weakly excites
  7. L0:1301 weakly suppresses
  8. L0:1955 weakly suppresses
  9. L0:1224 weakly suppresses
  10. L0:873 weakly suppresses
  11. L0:178 weakly suppresses
  12. L0:1240 weakly suppresses
  13. L0:1727 weakly excites
  14. L0:483 weakly excites
  15. L0:249 weakly excites ordinal suffix "nd" after numbers
  16. L0:1758 weakly excites
  17. L0:532 weakly excites
  18. L0:2283 weakly excites
  19. L0:2061 weakly excites
  20. L0:2323 weakly excites
  21. L0:1555 weakly suppresses
  22. L0:1556 weakly excites
  23. L0:1114 weakly excites
  24. L0:513 weakly suppresses

Feeds later layers

  1. L3:309 suppresses
  2. L2:584 weakly suppresses
  3. L3:2608 weakly suppresses
  4. L5:1839 weakly excites
  5. L6:819 weakly excites
  6. L18:170 weakly suppresses
  7. L15:1551 weakly excites
  8. L20:1628 weakly excites
  9. L2:1409 weakly suppresses
  10. L15:414 weakly excites
  11. L17:1847 weakly excites
  12. L15:1847 weakly excites
  13. L13:1851 weakly excites
  14. L9:115 weakly excites
  15. L25:1943 weakly suppresses
  16. L2:740 weakly excites
  17. L17:2683 weakly excites
  18. L6:165 weakly suppresses
  19. L4:112 weakly suppresses
  20. L4:616 weakly suppresses
  21. L16:2202 weakly excites
  22. L12:1071 weakly excites
  23. L18:1913 weakly suppresses
  24. L10:1320 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 -1.41 and -1.291 values between -1.29 and -1.171 values between -1.17 and -1.052 values between -1.05 and -0.936 values between -0.93 and -0.821 values between -0.82 and -0.703 values between -0.70 and -0.586 values between -0.58 and -0.4615 values between -0.46 and -0.34100 values between -0.34 and -0.22607 values between -0.22 and -0.101860 values between -0.10 and 0.021061 values between 0.02 and 0.14181 values between 0.14 and 0.2620 values between 0.26 and 0.389 values between 0.38 and 0.5010 values between 0.50 and 0.627 values between 0.62 and 0.745 values between 0.74 and 0.861 values between 0.86 and 0.982 values between 0.98 and 1.102 values between 1.10 and 1.221 values between 1.22 and 1.342 values between 1.34 and 1.461 values between 1.46 and 1.581 values between 1.70 and 1.821 values between 1.94 and 2.061 values between 3.26 and 3.38offnegativepositiveoften

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. oton
  2. ewis
  3. ativo
  4. 踏
  5. 对他们
  6. alars
  7. iversary
  8. tail
  9. setAddress
  10. 对未来

Suppresses

  1. ings
  2. ῇ
  3. clam
  4. egan
  5. чки
  6. чив
  7. ewidth
  8. .Deep
  9. êu
  10. jeta