Neuron Explorer

Qwen3-0.6B

'which' after 'find out' or 'choose'

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 fires on the word 'which' when it introduces a choice, such as 'to find out which', 'choose which' or 'predict which'. Its negative side is weak and tied to 'of' after 'each'. Turning it up did not give an obvious theme in the output.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    cell in the cytoplasm, to the ribosomes. There the information of the mRNAs is used for protein production (translation). The fundamental question was which of the two processes, i.e. transcription or translation, plays the dominant role

  2. #2 peak

    need to choose whatever sound we want to listen to. There are a lot of noises in the world that we don’t want to hear. We need to choose which sound that good for us. If we can’t choose, we will live our

  3. #3 peak

    on repeating patterns with shapes, sounds and actions. When we build our patterns we count to see how many shapes are in the core. We are learning to predict which shapes might come next. We are also learning about increasing and decreasing patterns and figuring

  4. #4 peak

    might have to check your risk for heart and blood vessel problems depend on your age, health, gender, and risk factors. Talk to your doctor to find out which tests are right for you.⏎Other Works Consulted⏎- Expert Panel on Integrated

  5. #5 peak

    ’t be performed, and that is called lactose intolerance. Many types of research show the benefits of almond and soy milk, but the question asked multiple times is which one is better? So, let’s find out by comparing these two kinds of

  6. #6 peak

    even sure exactly what that entails or means. We should be focusing on what the title suggests, NC History. The standards leave it up to the teacher to choose which events or people they prefer to teach about without a clear, concise plan. This

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 am trying to understand what I can do. I am trying to understand what I can do. I am trying to understand what I can do. I am trying to understand what I can do. I am trying to understand what I can

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

    healthy eating as defined by community members themselves.⏎This study includes three of the most deprived electoral wards in Stoke-on-Trent. In each of these areas, environmental factors including proximity of physical activity spaces, greenspace and leisure

  2. #2 peak

    assistance was required several times a day. For a description of what is included in each of these activities, please see the Glossary.<|endoftext|>Madison is preparing for battle

  3. #3 peak

    OMEN'S BOARDS ORGANIZED⏎After 1850, women organized mission societies that operated independent from maleled denominational boards. In each of five major Protestant denominations women set up mission boards to channel resources specifically toward women

  4. #4 peak

    into two major groups. Sections 1 through 7 tell the story of agriculture and farmworkers in our area by decade over the past thirty years.⏎In each of the Centerís three decades, certain ethnic communities have been prominent in the diverse farm

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. L0:1301 weakly suppresses
  2. L0:1284 weakly excites
  3. L0:1224 weakly suppresses
  4. L0:178 weakly suppresses
  5. L0:1345 weakly excites
  6. L0:1931 weakly suppresses
  7. L0:310 weakly excites
  8. L0:663 weakly excites
  9. L0:1058 weakly excites
  10. L0:2120 weakly suppresses
  11. L0:1 weakly suppresses
  12. L0:1459 weakly suppresses
  13. L0:1470 weakly suppresses
  14. L0:1717 weakly suppresses
  15. L0:275 weakly excites
  16. L0:1167 weakly suppresses
  17. L0:3040 weakly excites
  18. L0:588 weakly suppresses
  19. L0:2849 weakly excites
  20. L0:2183 weakly suppresses
  21. L0:2765 weakly excites
  22. L0:2848 weakly suppresses
  23. L0:377 weakly suppresses
  24. L0:382 weakly suppresses

Feeds later layers

  1. L2:147 excites
  2. L10:2949 weakly suppresses
  3. L10:167 weakly excites
  4. L3:58 weakly excites
  5. L3:2213 weakly suppresses
  6. L7:1683 weakly excites
  7. L27:2509 weakly excites
  8. L18:834 weakly excites
  9. L5:2546 weakly suppresses
  10. L2:1259 weakly excites
  11. L26:2362 weakly excites
  12. L2:918 weakly suppresses
  13. L7:2755 weakly excites
  14. L6:352 weakly excites
  15. L18:1420 weakly excites
  16. L14:854 weakly excites
  17. L19:1842 weakly suppresses
  18. L21:176 weakly excites
  19. L7:396 weakly excites
  20. L5:125 weakly suppresses "of" after all three, both, ten
  21. L13:1720 weakly suppresses
  22. L5:2784 weakly suppresses
  23. L4:285 weakly excites
  24. L7:883 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 -1.74 and -1.671 values between -0.78 and -0.702 values between -0.70 and -0.632 values between -0.63 and -0.554 values between -0.55 and -0.482 values between -0.48 and -0.409 values between -0.40 and -0.3315 values between -0.33 and -0.2682 values between -0.26 and -0.18303 values between -0.18 and -0.11726 values between -0.11 and -0.031426 values between -0.03 and 0.04904 values between 0.04 and 0.12314 values between 0.12 and 0.1982 values between 0.19 and 0.2617 values between 0.26 and 0.344 values between 0.34 and 0.413 values between 0.41 and 0.491 values between 0.49 and 0.563 values between 0.56 and 0.642 values between 0.64 and 0.711 values between 0.79 and 0.861 values between 0.86 and 0.931 values between 0.93 and 1.011 values between 1.01 and 1.081 values between 1.16 and 1.23offnegativepositiveoften

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. discipl
  2. ger
  3. door
  4. atcher
  5. ガー
  6. imin
  7. 电器
  8. doors
  9. ERING
  10. 不一样

Suppresses

  1. ropic
  2. edImage
  3. oundation
  4. pek
  5. ioc
  6. edm
  7. yah
  8. ém
  9. 裸
  10. +n