Neuron Explorer

Qwen3-0.6B

closing quote marks at the end of speech

A neuron in layer 11 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 at the end of a line of dialogue, where a sentence ends with a closing quotation mark and a line break. Turning it up did not make the model's output clearly about speech or quotes.

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

    drawing a picture of.⏎"God," he said.⏎"Why Johnny," she said, "you can't do thatbecause nobody knows what God looks like."⏎"They will when I'm finished," he assured her.⏎That story presents concret

  2. #2 peak

    -clad horsemen.⏎“I’ll wager that’s General Lee,” said the captain, with a glance at me. “Let us hope things turn out all right.”⏎As the two Federals neared the spot, a man arose and they exchanged

  3. #3 peak

    You quite shock me; if you mean a fling at the slave-trade, I assure you Mr. Suckling was always rather a friend to the abolition.”⏎“I did not mean, I was not thinking of the slave-trade,” replied Jane

  4. #4 peak

    already mention that you might have a rare disease?”⏎That was the first shock. “I might have what?”⏎She said: “A rare disease that is called Alpha 1 Antitry

  5. #5 peak

    Do you see the cell phone as sort of an arriviste, as someone that sort of came along and stole the thunder of the payphone?” Rocca asked.⏎“It stole its relevance. And it made communication so simple and so trivial even

  6. #6 peak

    “I sometimes think the western countries that are financially supporting this degradation process have no idea what they are destroying. There is nothing in Europe remotely like this river system.”⏎From the mountains of Greece where it is known as the Aoös, the V

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 thinking about lately, and I have been thinking about some of the most important things for me, like me, like, I have been thinking of me, like, and I have been thinking of me, like, and I

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

    his eyes up to the general. His mind and body seemed two separate things and the young soldier couldn’t stand at attention or even offer a salute. “I-I guess I can’t take it, sir,” Kuhl said.⏎The general’s

  2. #2 peak

    , and I had to have it removed. I really love birch trees, but I wonder if it's worth it to try planting one again.⏎A Yes, try again. Chances are good that a new birch will live long enough

  3. #3 peak

    the most common types of tomatoes available. They can be meaty like a beefsteak, but always juicy.⏎Vesuvio Piennolo<|endoftext|>Thank you to DadsWorksheets.com for providing a VARIETY of math practice sheets

  4. #4 peak

    might have what?”⏎She said: “A rare disease that is called Alpha 1 Antitrypsin Deficiency.”⏎I was confused. “What? What is this? How can I cure it? What do I do?” I

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. L2:3037 suppresses
  2. L6:2259 weakly suppresses
  3. L8:16 weakly suppresses
  4. L10:2351 weakly suppresses science news body text
  5. L8:10 weakly excites
  6. L10:2771 weakly suppresses
  7. L10:1878 weakly excites
  8. L9:933 weakly suppresses
  9. L10:624 weakly excites
  10. L8:2057 weakly suppresses
  11. L4:1687 weakly excites
  12. L0:1670 weakly suppresses
  13. L2:2041 weakly suppresses
  14. L5:364 weakly excites
  15. L4:310 weakly excites
  16. L10:2278 weakly suppresses
  17. L1:2444 weakly suppresses
  18. L4:2994 weakly suppresses
  19. L0:2192 weakly suppresses
  20. L6:1085 weakly excites
  21. L2:2502 weakly excites
  22. L10:36 weakly excites
  23. L10:2227 weakly suppresses
  24. L8:471 weakly suppresses

Feeds later layers

  1. L15:3036 excites
  2. L15:2027 weakly excites
  3. L15:2012 weakly excites
  4. L17:1266 weakly suppresses
  5. L12:67 weakly excites
  6. L13:2559 weakly suppresses
  7. L21:2349 weakly suppresses
  8. L23:2166 weakly suppresses
  9. L25:1044 weakly excites
  10. L13:2792 weakly suppresses
  11. L24:793 weakly suppresses
  12. L24:1932 weakly suppresses
  13. L12:2444 weakly suppresses
  14. L12:2413 weakly suppresses
  15. L13:2020 weakly excites
  16. L13:845 weakly excites
  17. L18:2123 weakly suppresses
  18. L19:152 weakly suppresses
  19. L18:1657 weakly suppresses
  20. L19:2013 weakly excites
  21. L24:1758 weakly suppresses the 'Ar' syllable inside names
  22. L16:3043 weakly suppresses
  23. L24:1046 weakly suppresses
  24. L20:2748 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 -2.13 and -1.941 values between -1.19 and -1.001 values between -1.00 and -0.8211 values between -0.63 and -0.44126 values between -0.44 and -0.25929 values between -0.25 and -0.061956 values between -0.06 and 0.13732 values between 0.13 and 0.31119 values between 0.31 and 0.5016 values between 0.50 and 0.693 values between 0.69 and 0.883 values between 0.88 and 1.073 values between 1.07 and 1.252 values between 1.44 and 1.631 values between 1.63 and 1.823 values between 2.01 and 2.191 values between 5.20 and 5.39offnegativepositiveoften

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. IFIER
  2. amide
  3. uating
  4. ائم
  5. ipients
  6. phans
  7. 玑
  8. uity
  9. lsi
  10. ossa

Suppresses

  1. TEM
  2. nore
  3. createElement
  4. ıklı
  5. VE
  6. raq
  7. ᾶ
  8. :"; ⏎
  9. 你也
  10. 榄