Neuron Explorer

Qwen3-0.6B

'to' after a noun that needs a purpose clause

A neuron in layer 7 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 'to' when it follows a noun or phrase and introduces what is needed or intended, as in 'how much exercise do we need to' or 'the minimum age to'. Turning it up made the writing drift toward numbers and counting problems.

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

    . Slovin's formula allows a researcher to sample the population with a desired degree of accuracy. It gives the researcher an idea of how large his sample size needs to be to ensure a reasonable accuracy of results. * When to Use Slovin's

  2. #2 peak

    at which ice sheets have ever been seen to move over rock and into the sea, both in Antarctica and in Greenland.⏎They then calculated how much ice would need to be released into the oceans in order for sea-levels to rise by 2

  3. #3 peak

    of 0.02). Plug your population size and required margin of error into the formula. The result will be the number of samples you need to take.⏎For example, suppose that you have a group of 1,0

  4. #4 peak

    MRI scan, so researchers will know how many children are needed to conduct a successful study. The team is also exploring ways to reassure children that an

  5. #5 peak

    Let’s assume that we have a more general problem. There are n questions, and a(n) is the smallest number of times we need to take the test to guarantee that we can figure out the answers. First we can try all combinations of

  6. #6 peak

    mentioned below:⏎- Will the illegalization of abortion increase backstreet abortions?⏎- How does abortion affect a woman’s health?⏎- What should be the minimum age to legally abort?⏎- What reasons exists behind the decision of abortion for married couples?⏎

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: For example, a rectangle is a rectangle. The second is a list of lists. For example, the second is a list of lists. The second is a list of lists. The second is a list of lists. The second is a

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

    to 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

  2. #2 peak

    ivut||678 - 687|⏎|Julkaisu||JOURNAL OF LANGUAGE TEACHING AND RESEARCH|⏎|DOI - pysyväislinkit

  3. #3 peak

    wind, a growing discontent with the French.Here Be Dragons⏎Trends of 'discontent'⏎View usage over:⏎'discontent' in Other Languages⏎Translation of discontent from the Collins English to Portuguese Dictionary<|endoftext|><the auberges in

  4. #4 peak

    -immune-system⏎- Kennedy, David O. “B Vitamins and the Brain: Mechanisms, Dose and Efficacy—A Review.” Nutrients, vol. 8, no. 2, Jan. 20

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. L6:442 excites
  2. L6:1674 weakly suppresses
  3. L6:2946 weakly excites
  4. L6:929 weakly suppresses
  5. L2:2772 weakly suppresses
  6. L6:1304 weakly suppresses
  7. L6:2606 weakly suppresses
  8. L1:2874 weakly suppresses
  9. L4:913 weakly excites
  10. L1:2813 weakly excites
  11. L6:1895 weakly excites
  12. L6:1217 weakly excites
  13. L5:326 weakly excites
  14. L6:1352 weakly suppresses
  15. L6:83 weakly excites
  16. L6:2029 weakly suppresses row and column words in grids and tables
  17. L6:1214 weakly suppresses
  18. L3:1546 weakly suppresses
  19. L2:1956 weakly suppresses
  20. L4:2023 weakly excites
  21. L5:1814 weakly excites
  22. L4:780 weakly excites
  23. L6:7 weakly suppresses
  24. L6:2055 weakly excites

Feeds later layers

  1. L12:2094 excites
  2. L13:2390 excites limits, thresholds and how long it takes
  3. L12:1088 excites
  4. L10:520 excites
  5. L12:2492 weakly excites
  6. L10:953 weakly excites
  7. L11:1367 weakly excites
  8. L12:1641 weakly excites
  9. L24:1427 weakly excites
  10. L27:615 weakly suppresses
  11. L8:2682 weakly suppresses
  12. L9:826 weakly excites
  13. L12:2632 weakly suppresses
  14. L18:1979 weakly excites
  15. L12:3045 weakly excites
  16. L13:1812 weakly excites
  17. L23:1009 weakly excites
  18. L15:776 weakly excites
  19. L9:1096 weakly excites
  20. L13:2415 weakly suppresses
  21. L12:1620 weakly suppresses
  22. L14:510 weakly suppresses
  23. L20:1098 weakly suppresses
  24. L16:1524 weakly suppresses unclear: document ends and species names

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 -1.32 and -1.191 values between -0.92 and -0.788 values between -0.65 and -0.5227 values between -0.52 and -0.38116 values between -0.38 and -0.25549 values between -0.25 and -0.121448 values between -0.12 and 0.021179 values between 0.02 and 0.15474 values between 0.15 and 0.2986 values between 0.29 and 0.4212 values between 0.42 and 0.564 values between 0.56 and 0.691 values between 0.69 and 0.821 values between 0.96 and 1.091 values between 3.90 and 4.04offnegativepositiveoften

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. odal
  2. .go
  3. garn
  4. INUX
  5. 遣
  6. reap
  7. del
  8. tallest
  9. go
  10. Hits

Suppresses

  1. �回
  2. [class
  3. ceiver
  4. [Boolean
  5. )t
  6. 比利时
  7. ASF
  8. enders
  9. [P
  10. )m