Neuron Explorer

Qwen3-0.6B

words that introduce a clause

A neuron in layer 10 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 small word right before a new statement begins, most often "that" after verbs like "tell", "show" or "advise", as in "shows that" or "Tell students that". Turning it up didn't produce a clear theme in the sample outputs, so its job is only partly understood.

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

    came up with an innovative robot design. They added a tail to their robot "Tailbot," which is essentially a toy car with a tail attached. It turns out that robot design could become much more than just a research tool.⏎Team leader Robert

  2. #2 peak

    your employees⏎Do a small search online, and you’ll soon find out that there are many different technical skills out there. But which ones are the most important

  3. #3 peak

    watered with rain and tap water, because they have more minerals for growth.⏎First, I had to decide what plant to test. After researching this, I decided to do bean plants, due to the quick speeds that they grow at. My

  4. #4 peak

    provides students with the opportunity to work with complex shapes to find surface area in a given context.⏎Display the image for all to see throughout the activity. Tell students that they calculated the volume of this heart-shaped box in a previous lesson and today they

  5. #5 peak

    describe graphs.⏎Can you find examples on the cards that match each definition? Can you draw some more examples of your own?<|endoftext|>Since 2012, the global economy has been experiencing average growth rates of less than 3 percent.

  6. #6 peak

    enough to allow entry for a fully-equipped firefighter.⏎- For determining egress window sizes and placement, the International Building Code advises that every bedroom must contain at least one egress window. It must be at least

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: The role of a leader in the company. The company and the organization that is being led by the person in question. What about? This is a problem. The company is led by the person in question. The problem of the company.

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

    through all of it.⏎So what’s the key? Goals have to be actionable. That is the only way to make sure they will know what steps to take, and don’t waste valuable

  2. #2 peak

    without the benefit of God’s grace and mercy. Because of his own sin, Saul found himself in a hopeless predicament, and killed himself. Only in the sense that God’s word was the immovable object against which Saul rebelled could it

  3. #3 peak

    Most of us recognize this from our own lives. We cannot become who we are without caring for the relations that care for us.⏎David Brooks called this the meaning of covenant, the bond between singular persons that protects not private interests (as contracts do

  4. #4 peak

    substance, so that one is consumed in the process. Anyone who wants to comprehend Christ’s message of light … must comprehend this one thing: the mission, the duty to shine, to draw others, to see, to heal, to do good

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. L8:2452 excites
  2. L8:894 suppresses
  3. L5:2901 weakly suppresses
  4. L7:1834 weakly excites
  5. L6:2089 weakly excites
  6. L8:172 weakly excites
  7. L8:1260 weakly excites
  8. L8:1608 weakly suppresses
  9. L6:686 weakly excites
  10. L9:265 weakly excites
  11. L6:2301 weakly suppresses
  12. L4:2929 weakly excites
  13. L2:1593 weakly suppresses
  14. L1:731 weakly suppresses
  15. L6:759 weakly excites
  16. L7:2568 weakly excites
  17. L9:1874 weakly suppresses
  18. L7:2205 weakly suppresses
  19. L6:1700 weakly excites
  20. L7:3009 weakly suppresses
  21. L9:1353 weakly excites
  22. L6:666 weakly excites
  23. L6:1123 weakly suppresses
  24. L3:972 weakly excites

Feeds later layers

  1. L18:2701 excites
  2. L11:1546 weakly suppresses
  3. L12:1420 weakly excites digits starting a percentage or rate
  4. L18:1960 weakly suppresses
  5. L21:656 weakly excites
  6. L12:1141 weakly suppresses
  7. L20:220 weakly suppresses
  8. L23:2027 weakly excites
  9. L24:89 weakly excites
  10. L11:2 weakly suppresses unclear: blank before a year or number
  11. L13:2766 weakly suppresses
  12. L14:1594 weakly excites
  13. L17:295 weakly suppresses
  14. L19:2564 weakly excites "be" after a modal verb
  15. L12:835 weakly excites
  16. L12:1324 weakly excites
  17. L15:2523 weakly excites
  18. L11:1072 weakly excites
  19. L17:2152 weakly excites
  20. L21:2091 weakly excites
  21. L16:2728 weakly excites
  22. L14:1738 weakly suppresses
  23. L15:1652 weakly suppresses
  24. L13:1912 weakly 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.

2 values between -1.81 and -1.681 values between -1.68 and -1.552 values between -1.55 and -1.413 values between -1.41 and -1.283 values between -1.28 and -1.1513 values between -1.15 and -1.0117 values between -1.01 and -0.8817 values between -0.88 and -0.7540 values between -0.75 and -0.6155 values between -0.61 and -0.48103 values between -0.48 and -0.35182 values between -0.35 and -0.21511 values between -0.21 and -0.081938 values between -0.08 and 0.05670 values between 0.05 and 0.19213 values between 0.19 and 0.3269 values between 0.32 and 0.4525 values between 0.45 and 0.5917 values between 0.59 and 0.727 values between 0.72 and 0.853 values between 0.85 and 0.998 values between 0.99 and 1.122 values between 1.12 and 1.252 values between 1.25 and 1.392 values between 1.39 and 1.521 values between 1.52 and 1.651 values between 2.32 and 2.451 values between 3.39 and 3.52offnegativepositiveoften

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. 的气息
  2. gyr
  3. 容忍
  4. Jaune
  5. $ar
  6. にする
  7. AREST
  8. 蟠
  9. /rs
  10. 很开心

Suppresses

  1. ension
  2. ensity
  3. W
  4. ie
  5. w
  6. �
  7. 引
  8. lli
  9. mega
  10. uality