Neuron Explorer

Qwen3-0.6B

'the' after across, around or of

A neuron in layer 14 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 "the" in phrases about wide places or whole groups, like "around the world", "across the country" or "and the elderly". Turning it up made the model repeat simple sentences about the sun and weather, which is only loosely related.

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

    drives. But IBM’s ideas still rely on the use of a magnetic field to store that data.⏎Researchers from around the world are collaborating on solving the speed problem, and they’ve come up with a

  2. #2 peak

    ers during the French religious wars, Mercier was obliged to take refuge in Venice in 1567 and, after returning to France, he died of the plague. One of his best-known works was the Libellus de abbrevi

  3. #3 peak

    confusing, punctuation marks.⏎From Afghanistan to Zimbabwe, discover surprising and intriguing language facts from around the globe.⏎The definitions of ‘buddy’ and ‘bro’ in the O

  4. #4 peak

    can be mixed. This could be because of already mentioned approximate land type detection. In<|endoftext|>Nutrition plays a very important role in the lives of both young and old. However for seniors, it’s important to be aware of new studies on how

  5. #5 peak

    the article.⏎The latest study followed a group of nuns, monks and priests from across the United States over a period of 12 years. They were chosen as a

  6. #6 peak

    those who experience it. Unfortunately, despite efforts to raise awareness and implement preventative measures, instances of sexual harassment continue to occur in schools, colleges, and universities across the country.⏎In Pakistan, schools, colleges, and universities are considered to be safe

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 think of a system of equations of the first order and the system of equations of the first order of the system of equations of the first order of the system of equations of the first order of the system of equations of the first order of

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

    Whooper,"<|endoftext|>AttachmentsAccessible Version Accessible version of the tutorial content in PDF format⏎Source and Access Information⏎Aligned StandardsThis vetted resource aligns to concepts or skills in these benchmarks.⏎In this interactive tutorial, learn about the major factors

  2. #2 peak

    listen to and obey His voice⏎Jeremiah 7:28 "And you shall say to them, 'This is the nation that did not obey the voice of the LORD their God or accept correction; truth has perished and has been

  3. #3 peak

    at Mount Sinai when G-d descended upon the mountain and gave us His Torah. As it says: “Only beware and guard yourself carefully, lest you forget the things your eyes have seen and lest they stray from your heart all the days of your

  4. #4 peak

    great joy that will be for all the people. 11 For unto you is born this day in the city of David a Savior, who is Christ the Lord. 12 And this

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. L11:1145 suppresses 'of' inside institution names
  2. L5:136 suppresses
  3. L5:636 weakly suppresses
  4. L1:376 weakly suppresses
  5. L13:1204 weakly suppresses
  6. L13:846 weakly suppresses
  7. L12:521 weakly suppresses
  8. L10:120 weakly suppresses
  9. L11:199 weakly suppresses
  10. L13:2746 weakly suppresses
  11. L11:1747 weakly suppresses
  12. L10:352 weakly suppresses
  13. L13:2267 weakly excites
  14. L8:15 weakly suppresses unclear: mid-phrase words across many languages
  15. L5:511 weakly suppresses
  16. L11:137 weakly suppresses
  17. L7:938 weakly excites
  18. L9:1351 weakly suppresses
  19. L12:1598 weakly suppresses
  20. L10:1388 weakly excites
  21. L13:1535 weakly suppresses
  22. L13:1952 weakly suppresses
  23. L1:1576 weakly excites
  24. L13:633 weakly suppresses

Feeds later layers

  1. L16:1465 suppresses
  2. L17:2783 suppresses
  3. L15:942 excites
  4. L18:1672 suppresses
  5. L19:2815 suppresses
  6. L15:435 excites
  7. L15:1902 suppresses
  8. L18:2370 suppresses
  9. L15:1226 suppresses
  10. L15:2547 suppresses
  11. L20:450 suppresses
  12. L15:2079 excites
  13. L16:749 excites
  14. L15:702 excites
  15. L18:1011 excites
  16. L19:241 excites
  17. L21:1422 suppresses
  18. L17:181 suppresses
  19. L15:1848 suppresses
  20. L18:898 excites
  21. L15:2893 suppresses
  22. L22:429 suppresses
  23. L16:1441 excites
  24. L17:2037 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 -1.71 and -1.591 values between -1.48 and -1.363 values between -1.24 and -1.122 values between -1.12 and -1.015 values between -1.01 and -0.897 values between -0.89 and -0.7716 values between -0.77 and -0.6512 values between -0.65 and -0.5428 values between -0.54 and -0.4251 values between -0.42 and -0.30141 values between -0.30 and -0.18558 values between -0.18 and -0.071940 values between -0.07 and 0.05724 values between 0.05 and 0.17247 values between 0.17 and 0.2971 values between 0.29 and 0.4035 values between 0.40 and 0.5215 values between 0.52 and 0.6417 values between 0.64 and 0.7611 values between 0.76 and 0.875 values between 0.87 and 0.992 values between 0.99 and 1.113 values between 1.11 and 1.223 values between 1.22 and 1.344 values between 1.34 and 1.461 values between 1.58 and 1.691 values between 1.69 and 1.811 values between 1.81 and 1.931 values between 2.16 and 2.281 values between 2.75 and 2.871 values between 2.87 and 2.98offnegativepositiveoften

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. DNS
  2. frey
  3. doom
  4. 戴上
  5. iband
  6. DDD
  7. eeper
  8. 的关注
  9. surrounded
  10. 的理解

Suppresses

  1. nants
  2. isting
  3. orian
  4. -login
  5. roup
  6. 我在
  7. bable
  8. noss
  9. ofApp
  10. unist