Neuron Explorer

Qwen3-0.6B

signs and constants in equations

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 plus and minus signs and small numbers inside maths formulas, such as the '+ 1' in n + 1 or the '2' in a parabola equation. It is weak and mixed, so it is hard to say more than that. Turning it up did not produce a clear change in the replies.

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

    is the liturgy celebrated?⏎- Where is the liturgy celebrated?<|endoftext|>A particle is moving along the parabola 4y = (x + 2)^2 in such a way that its x-coordinate is increasing at a constant rate

  2. #2 peak

    5 Y 2 . Solution : X =- 5 W c) Find some solution of A X = 3 Y

  3. #3 peak

    ⏎Atomic Symbol: Rn⏎Atomic Weight: 222⏎Melting Point: -95 F (-71 C)⏎Boiling Point: -79 F (-61.7 C)⏎Word origin: The word rad

  4. #4 peak

    are parallel.⏎Hence, the given lines are parallel.⏎Let's consider another set of equations.⏎y = 2x +3 and 4y = –2x+10⏎On comparing y = 2x +3 and

  5. #5 peak

    ` initialized to 1, increment⏎it each round through the loop, and check it before running the loop. When the⏎check indicates that it equals n + 1 (

  6. #6 peak

    ) you will obtain your answer:⏎F'(x) = 2x√(1+x6)⏎Comment. There is no need to integrate and then differentiate by x.⏎

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 using the following code: (A, B) where A and B are the values, and I used the values, and the code that I can be used for a small number of (A, B) is the first

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

    - Filed Under⏎J ennifer Skaja has seen the signs of small miracles, as children

  2. #2 peak

    CO2 + H2O.⏎How does baking soda and vinegar make a chemical reaction?⏎Can you

  3. #3 peak

    generally share the communitarian position on issues relating to the economy, such as the need for environmental protection and public education, but not on cultural<|endoftext|>Cite This Page⏎Louisa Musgrove Timeline and Summary⏎- Louisa and her

  4. #4 peak

    to explore STEM topics in a way that deepens their knowledge while also developing 21st-century skills.⏎Read the rest of this entry »⏎Filed under: Gaming, Services, Software, 3 million dollar grant, Associate Professor, Aug

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. L9:1988 strongly suppresses
  2. L7:678 suppresses
  3. L6:1187 suppresses
  4. L8:1305 weakly suppresses
  5. L9:327 weakly excites
  6. L4:722 weakly excites
  7. L9:589 weakly excites
  8. L4:1056 weakly excites
  9. L0:1133 weakly suppresses
  10. L8:1162 weakly suppresses
  11. L3:2196 weakly suppresses
  12. L9:1249 weakly excites
  13. L7:2569 weakly suppresses
  14. L4:2927 weakly excites
  15. L9:1834 weakly excites
  16. L5:163 weakly suppresses
  17. L9:2414 weakly suppresses
  18. L8:1217 weakly excites
  19. L4:1947 weakly suppresses
  20. L4:2622 weakly excites
  21. L1:1582 weakly excites
  22. L3:2127 weakly excites
  23. L3:2093 weakly excites
  24. L5:1475 weakly excites

Feeds later layers

  1. L18:137 suppresses 'the' after 'to' in fixed phrases
  2. L17:399 suppresses
  3. L11:689 excites
  4. L20:164 suppresses
  5. L18:365 suppresses
  6. L11:1515 excites
  7. L16:1066 suppresses
  8. L17:765 weakly suppresses
  9. L18:344 weakly excites
  10. L11:1659 weakly excites
  11. L19:643 weakly suppresses
  12. L27:672 weakly suppresses
  13. L22:2254 weakly suppresses
  14. L18:404 weakly excites 'get', 'go' and 'got' after a subject
  15. L26:2674 weakly suppresses
  16. L27:2672 weakly suppresses word-start 't' fragment in split words
  17. L26:2002 weakly excites the "un" prefix splitting a word
  18. L26:2552 weakly suppresses
  19. L22:316 weakly suppresses
  20. L16:827 weakly suppresses
  21. L24:1837 weakly excites
  22. L20:1070 weakly excites
  23. L25:189 weakly suppresses
  24. L27:1887 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.

2 values between -0.43 and -0.406 values between -0.40 and -0.375 values between -0.37 and -0.343 values between -0.34 and -0.319 values between -0.31 and -0.2728 values between -0.27 and -0.2438 values between -0.24 and -0.2138 values between -0.21 and -0.1876 values between -0.18 and -0.15119 values between -0.15 and -0.12201 values between -0.12 and -0.09290 values between -0.09 and -0.05437 values between -0.05 and -0.02626 values between -0.02 and 0.01588 values between 0.01 and 0.04423 values between 0.04 and 0.07297 values between 0.07 and 0.10232 values between 0.10 and 0.14172 values between 0.14 and 0.17107 values between 0.17 and 0.2073 values between 0.20 and 0.2347 values between 0.23 and 0.2629 values between 0.26 and 0.2925 values between 0.29 and 0.3217 values between 0.32 and 0.366 values between 0.36 and 0.398 values between 0.39 and 0.423 values between 0.42 and 0.451 values between 0.45 and 0.481 values between 0.51 and 0.541 values between 0.80 and 0.83offnegativepositiveoften

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. aption
  2. waves
  3. oods
  4. forcer
  5. went
  6. ueva
  7. rica
  8. ackson
  9. 口水
  10. wife

Suppresses

  1. té
  2. ied
  3. UnderTest
  4. antage
  5. 첨
  6. /jav
  7. contemplate
  8. ertiary
  9. juan
  10. typeid