Neuron Explorer

Qwen3-0.6B

unclear: quantity and choice words

A neuron in layer 14 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron seems to respond to words that set up a choice or a range, such as 'both', 'neither', 'of' in a list, or numbers like 'Years 10 and 11'. The link is weak. Turning it down made the model repeat 'the following' over and over.

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

    plays, poetry and non-fiction texts.⏎All our teachers are English specialists.⏎For more information contact the head of department, Miss S Beadle.⏎In Years 10 and 11, all pupils study for the AQA GCSE English

  2. #2 peak

    , more than 200 social scientists (including myself) who study games in the fields of psychology and communication among others, signed a statement urging the American Psychological Association to repeal

  3. #3 peak

    Katherine who was neither divorced, beheaded, or died. She was by any standards a remarkable woman: beautiful enough to marry the King of England, despite having neither royal nor court background; shrewd enough to remain his Queen, despite court

  4. #4 peak

    ulsions. While the motion of single particles in Newtonian fluids is well understood, suspensions of large numbers of particles that interact through the fluid remain challenging, both analytically and numerically. A complicating factor is that in many application

  5. #5 peak

    opportunity to consume fruit and vegetables in abundance as well as quality protein, whole grains and low-fat dairy products or affordable plant milks. Regular, physical activity (both weight-bearing for musculoskeletal health benefits and intensive for cardiovascular health benefits) would

  6. #6 peak

    , 8 and 10 students take a writing test which consists of an essay and multiple choice questions. A reading and mathematics test is given in grades 3 through 10. In grades 5, 8

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 the following questions: 1. I have the following questions: 1: I have the following: 1: The following: 1: The following: 1: The following: 1: The following: 1: The following: 1:

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

    general informational purposes only and is not a substitute for professional medical advice.⏎If you think you may have a medical emergency, call your doctor or (in the United States) 911 immediately. Always seek the advice of your doctor before starting

  2. #2 peak

    to those found in human blood. The most significant elements are:⏎Sea vegetables are also a rich source of fiber and protein, with some varieties containing up to 28% protein. They are also an excellent supply of vitamins A,

  3. #3 peak

    , how do you know if your baby is ready? Babies show certain signs of development or growth, which indicate they're ready to eat solid foods. One such sign is their ability to chew and swallow. There are some important signs of readiness,

  4. #4 peak

    and, Massachusetts, can be seen scurrying about the freshly dug school garden planting Swiss chard, spinach, peas, and pumpkin seeds. The first three items will be harvested by mid-June to make way for a second crop.⏎

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. L12:42 suppresses
  2. L13:2381 suppresses
  3. L13:1675 excites
  4. L13:1063 suppresses
  5. L13:1731 excites
  6. L13:2006 suppresses
  7. L7:385 suppresses
  8. L11:172 suppresses
  9. L12:1189 excites
  10. L12:1873 excites
  11. L1:951 suppresses
  12. L13:1895 suppresses
  13. L13:2782 weakly excites
  14. L12:763 weakly suppresses
  15. L13:562 weakly excites
  16. L9:112 weakly suppresses
  17. L12:21 weakly suppresses
  18. L13:199 weakly suppresses
  19. L12:1814 weakly suppresses
  20. L13:328 weakly excites
  21. L12:1894 weakly suppresses
  22. L13:749 weakly excites
  23. L12:1087 weakly suppresses
  24. L12:463 weakly excites

Feeds later layers

  1. L16:2950 strongly suppresses
  2. L18:1746 strongly suppresses
  3. L16:2677 suppresses
  4. L15:709 suppresses
  5. L19:2423 suppresses
  6. L16:1127 excites opening bracket after an imperial measurement
  7. L18:486 excites
  8. L19:254 excites
  9. L17:1462 suppresses
  10. L17:2130 suppresses
  11. L15:247 excites
  12. L16:1039 suppresses
  13. L17:234 excites
  14. L18:2649 suppresses
  15. L16:473 suppresses
  16. L18:2872 suppresses
  17. L16:2568 suppresses
  18. L18:1978 suppresses
  19. L15:1994 suppresses
  20. L19:2131 suppresses
  21. L15:1679 suppresses
  22. L18:2867 suppresses
  23. L16:2801 suppresses
  24. L16:2748 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 -2.66 and -2.492 values between -2.49 and -2.331 values between -2.33 and -2.161 values between -2.16 and -2.006 values between -2.00 and -1.838 values between -1.83 and -1.6711 values between -1.67 and -1.5111 values between -1.51 and -1.3428 values between -1.34 and -1.1840 values between -1.18 and -1.0178 values between -1.01 and -0.85137 values between -0.85 and -0.68196 values between -0.68 and -0.52352 values between -0.52 and -0.36537 values between -0.36 and -0.19699 values between -0.19 and -0.03675 values between -0.03 and 0.14404 values between 0.14 and 0.30278 values between 0.30 and 0.47164 values between 0.47 and 0.63101 values between 0.63 and 0.8054 values between 0.80 and 0.9641 values between 0.96 and 1.1229 values between 1.12 and 1.2914 values between 1.29 and 1.4512 values between 1.45 and 1.6211 values between 1.62 and 1.783 values between 1.78 and 1.955 values between 1.95 and 2.112 values between 2.11 and 2.273 values between 2.27 and 2.441 values between 2.60 and 2.772 values between 2.77 and 2.931 values between 3.75 and 3.92offnegativepositiveoften

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. arella
  2. |_|
  3. (Level
  4. ory
  5. 唧
  6. IRON
  7. yours
  8. getProperty
  9. 意大
  10. ures

Suppresses

  1. 两个
  2. 两种
  3. 这三个
  4. 三个
  5. 三种
  6. 这两个
  7. arı
  8. both
  9. 哪些
  10. 这两种