Neuron Explorer

Qwen3-0.6B

math word problems and worksheets

A neuron in layer 10 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 fires on math teaching text, especially words like 'problem', 'word problems' and 'numbers' in worksheets and lessons. Turning it up pushed the writing toward problems and numbers, though the text got muddled. Turning it down made it repeat itself.

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

    email@example.com.<|endoftext|>Table of Contents :⏎Top Suggestions Senior Kindergarten Writting Worksheet :⏎Senior Kindergarten Writting Worksheet In this worksheet your students will practice their handwriting skills by tracing the

  2. #2 peak

    39 = 611 candles.⏎Using a bar diagram⏎In the bar diagram, the relationship is clear. This is a simple, one-step problem.⏎650 – 39 = 611 candles sold.⏎

  3. #3 peak

    ing (2-digits & 3-digits)⏎✔ Subtraction with and without regrouping (2-digits & 3-digits)⏎✔ Word Problems: addition, subtraction, and multiplication⏎✔ Addition Fact Fluency⏎✔ Sub

  4. #4 peak

    know multiplying fractions do not require the same denominators. So click and give it a try. It's easier than you think.⏎Fractions - Subtracting Mixed Numbers⏎Do you wonder how to subtract mixed numbers? Do you know how to handle

  5. #5 peak

    so PLEASE, PLEASE leave a comment if you LOVE your math series! I'd love to check it out!⏎I like the tricks (9s trick, Doubles, Doubles Plus 1) that Saxon uses to teach facts, but

  6. #6 peak

    How many candles did they sell?⏎This is much like a 2nd-grade problem, but with larger numbers. The main difficulty is to convert the common-sense

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: "This is a bird's eye view. It's the first thing you see. You take the first step. You take the first step. You take the first step. You take the first step. You take the first step. You

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

    time should focus on four critical areas: (1) developing understanding of and applying proportional relationships; (2) developing understanding of operations with rational numbers and working with expressions and linear equations; (3) solving problems involving

  2. #2 peak

    draw and write to show their mathematical thinking.⏎Contents 4-8 Counting and Cardinality Task Cards (CC) 9-13 Numbers and Operations in Base Ten Task Cards (NBT) 14-18 Operations and

  3. #3 peak

    before returning it to the shelf. Through time, the child refines their grip of the paintbrush. What a gentle, inviting way to learn how to later hold a pencil for writing!⏎Why are art activities important?⏎Dr. Montessori

  4. #4 peak

    language. Octave has extensive tools for solving common numerical linear algebra problems, finding the roots of nonlinear equations, functions written in Octave's own

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. L7:573 suppresses
  2. L7:2349 suppresses
  3. L6:1552 suppresses
  4. L6:1840 weakly excites
  5. L9:1453 weakly suppresses
  6. L7:2093 weakly suppresses
  7. L9:2665 weakly excites
  8. L9:1547 weakly suppresses
  9. L7:909 weakly excites
  10. L8:1709 weakly suppresses
  11. L6:987 weakly suppresses
  12. L2:1307 weakly suppresses
  13. L7:494 weakly excites
  14. L6:2406 weakly excites
  15. L6:1073 weakly excites
  16. L9:2930 weakly suppresses
  17. L6:2613 weakly excites
  18. L6:2362 weakly suppresses
  19. L2:2369 weakly excites
  20. L8:950 weakly suppresses
  21. L3:2474 weakly excites
  22. L7:121 weakly suppresses
  23. L8:2344 weakly excites
  24. L7:611 weakly suppresses

Feeds later layers

  1. L21:2366 excites
  2. L13:2592 excites
  3. L11:924 excites
  4. L11:1119 excites
  5. L11:1295 excites
  6. L22:2870 weakly suppresses
  7. L12:777 weakly excites
  8. L17:1656 weakly excites
  9. L11:3044 weakly excites
  10. L11:661 weakly excites
  11. L23:269 weakly excites
  12. L18:2371 weakly excites
  13. L21:410 weakly excites
  14. L18:387 weakly suppresses
  15. L13:107 weakly excites
  16. L17:2349 weakly excites
  17. L15:2634 weakly excites
  18. L18:140 weakly excites
  19. L11:1183 weakly suppresses
  20. L17:1393 weakly suppresses
  21. L21:1363 weakly excites
  22. L21:2739 weakly excites
  23. L11:1661 weakly excites
  24. L22:2277 weakly suppresses

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 -1.20 and -1.082 values between -0.97 and -0.852 values between -0.85 and -0.743 values between -0.74 and -0.621 values between -0.62 and -0.5120 values between -0.51 and -0.3971 values between -0.39 and -0.28275 values between -0.28 and -0.16787 values between -0.16 and -0.041401 values between -0.04 and 0.07892 values between 0.07 and 0.19349 values between 0.19 and 0.3081 values between 0.30 and 0.4210 values between 0.42 and 0.533 values between 0.53 and 0.651 values between 0.65 and 0.762 values between 0.76 and 0.881 values between 0.99 and 1.112 values between 1.11 and 1.221 values between 1.22 and 1.341 values between 1.45 and 1.571 values between 2.61 and 2.721 values between 3.30 and 3.41offnegativepositiveoften

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. astos
  2. 題
  3. _cases
  4. casos
  5. 题目
  6. ést
  7. äsent
  8. cases
  9. -str
  10. exercises

Suppresses

  1. 六个月
  2. (IT
  3. 人流
  4. [,
  5. 当晚
  6. PRI
  7. 心跳
  8. offending
  9. "],["
  10. 排名第一