Neuron Explorer

Qwen3-0.6B

'see' in 'let's see' and 'to see if'

A neuron in layer 4 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 lights up on the word 'see' when it is used as 'let's see' or 'to see if', meaning check or find out. Turning it up made the model drift into math-style text, which does not clearly match the pattern.

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

    riting about those points to see which might make a useful topic. It allows them some room to explore potential topics

  2. #2 peak

    gave his recessive allele, they would have a 25% chance that their offspring would have this autosomal recessive trait or disorder.⏎So let's see what would happen if one parent was heterozygous and one parent was homo

  3. #3 peak

    looks at all the papers of all the students to see if having 89 identical answers is unusual, for students scoring the way John

  4. #4 peak

    through all of the answer options and eliminate choices that are obviously incorrect. In addition, it’s helpful to plug each answer option into the sentence and read it to see if it makes sense. Students who want to take advantage of these and other strategies

  5. #5 peak

    about it! Check out the brainteasers below to see the power of the brain in action, and answer the questions at the bottom of

  6. #6 peak

    Answer: Lines with the same slope are parallel and if the slope of one line is the negative reciprocal of the second line, then they are perpendicular.⏎Let's see how to identify parallel and perpendicular lines.⏎Let's take some examples to understand 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: $ \frac{1}{n} $, $ \frac{1}{n} $, and $ \frac{1}{n} $, and $ \frac{1}{n} $, and $ \frac{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

    of a risky asset is a random walk with drift, so its return is unpredictable."⏎4. Is the following statement true, false

  2. #2 peak

    answer specifies that the density function is⏎I got the f(x) = x-1 part, and I got how to calculate the variance after you have the expected values, but I'm lost on other questions.⏎My questions are:⏎Where do

  3. #3 peak

    tree-liana interactions: distribution and host preference of lianas in a tropical dry evergreen forest in India.⏎Vivek, P., & Parthasarathy, N.⏎Lianas are structurally dependent life-form that rely mostly on

  4. #4 peak

    implemented the law of giving a right to recall to the employers of certain industries. This law has been

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. L3:2204 excites
  2. L3:810 excites
  3. L3:461 excites
  4. L2:1113 weakly excites
  5. L3:1793 weakly suppresses
  6. L1:1910 weakly excites
  7. L0:1346 weakly excites
  8. L1:2858 weakly suppresses 'as' in Incas, 'te' in intelligence
  9. L3:3064 weakly excites
  10. L0:903 weakly excites
  11. L3:2673 weakly suppresses
  12. L2:1036 weakly excites
  13. L2:2653 weakly excites
  14. L3:388 weakly excites
  15. L1:29 weakly suppresses
  16. L1:782 weakly suppresses
  17. L2:75 weakly suppresses
  18. L3:777 weakly suppresses
  19. L3:1082 weakly suppresses
  20. L3:1119 weakly suppresses
  21. L0:170 weakly excites
  22. L1:898 weakly suppresses
  23. L2:126 weakly excites
  24. L3:2722 weakly suppresses

Feeds later layers

  1. L5:1690 suppresses
  2. L19:1511 suppresses
  3. L19:1753 weakly suppresses
  4. L20:826 weakly suppresses
  5. L23:1428 weakly suppresses
  6. L23:1981 weakly suppresses
  7. L23:2567 weakly suppresses
  8. L6:2031 weakly suppresses
  9. L5:740 weakly suppresses
  10. L12:682 weakly excites
  11. L13:2122 weakly suppresses
  12. L7:1006 weakly suppresses
  13. L5:2212 weakly suppresses
  14. L6:697 weakly suppresses
  15. L8:77 weakly suppresses
  16. L7:2720 weakly suppresses
  17. L7:1072 weakly suppresses
  18. L22:582 weakly suppresses
  19. L23:588 weakly suppresses
  20. L18:2836 weakly excites
  21. L15:2067 weakly excites
  22. L7:2277 weakly suppresses
  23. L9:1622 weakly excites
  24. L13:2469 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.

3 values between -0.41 and -0.3622 values between -0.36 and -0.3142 values between -0.31 and -0.25109 values between -0.25 and -0.20220 values between -0.20 and -0.15339 values between -0.15 and -0.10573 values between -0.10 and -0.04822 values between -0.04 and 0.01705 values between 0.01 and 0.06473 values between 0.06 and 0.12299 values between 0.12 and 0.17161 values between 0.17 and 0.2269 values between 0.22 and 0.2839 values between 0.28 and 0.3318 values between 0.33 and 0.384 values between 0.38 and 0.434 values between 0.43 and 0.491 values between 0.49 and 0.541 values between 0.54 and 0.591 values between 0.59 and 0.651 values between 0.91 and 0.961 values between 1.44 and 1.491 values between 1.65 and 1.70offnegativepositiveoften

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. affe
  2. ARN
  3. 胱
  4. rame
  5. ramework
  6. 学校
  7. ARSE
  8. Phar
  9. alte
  10. search

Suppresses

  1. izer
  2. 跌破
  3. izing
  4. .databind
  5. :";⏎
  6. decreasing
  7. 她说
  8. Specifications
  9. creasing
  10. -legged