Neuron Explorer

Qwen3-0.6B

"than" after "more to it" comparisons

A neuron in layer 6 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 "than" in phrases like "there is more to it than" or "goes a lot further than", where something is being said to be more than a simple version. Turning it up or down did not give a clear change in the written text.

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

    and well-being. Most people think being a dentist means putting your fingers in people’s mouths and looking for cavities, but there’s a lot more to it than that. Dentists work in lots of places outside the dental office, including hospitals

  2. #2 peak

    under domestic trade rules are permissible and viable options according to international norms, but showing favoritism for one industry at the expense of others can do far more harm than good. It is time for the U.S. government to stop implementing special interest

  3. #3 peak

    the incident light meter lux→EV standard is all about? Is it just an average-this-probably-will-work value, or is there more to it than that? And if it is just an average, what knowledge is necessary<|endoftext|>from

  4. #4 peak

    While some may question how much solving six problems of their choosing could possibly be of much benefit to students, there's actually a whole lot more going into this assignment than just solving six math problems. Students become familiar with the layout of a newspaper,

  5. #5 peak

    the environment in a number of ways1?⏎1) Cut Your Greenhouse Gas Emissions⏎The impact of animal agriculture on greenhouse gas emissions goes a lot further than just cows producing methane gas. Meat production requires vast amounts of energy. Not only

  6. #6 peak

    ⏎There is more to mantis shrimp than meets the eye. They pack a punch, decimating their prey using deadly strikes

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: if I can have a lot of people in the group, and if I can have a lot of people in the family of the people of the country. (The first time and the second time) of the said problem in the family.

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

    nickname of “imperial city”, envied by kings like Charles V. The expression “Vale un potosi!” (it costs a potosi

  2. #2 peak

    ser to the Sun doesn’t mean warmer⏎Mercury is the closest planet to the Sun. So it would make sense that this is the hottest planet,

  3. #3 peak

    Classes define the behavior for objects of its type. Instances of the class Class represent classes and interfaces in a running Java application. If we do not explicitly write a constructor for a class, the Java compiler builds a default constructor for that class. so

  4. #4 peak

    well as technical. Most employer surveys do, however, note that personal skills have at least equal rating with technical skills or qualifications for example;⏎In the Confederation of British Industries Education and Skills Survey: 2015, employers state:

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. L5:1580 strongly excites
  2. L2:1774 excites
  3. L4:221 excites
  4. L2:7 suppresses
  5. L1:55 excites
  6. L4:646 weakly excites
  7. L4:1654 weakly suppresses
  8. L1:2723 weakly suppresses mid-word syllables in capitalised names
  9. L4:1591 weakly excites
  10. L2:3006 weakly excites
  11. L1:721 weakly excites
  12. L0:2622 weakly suppresses
  13. L5:2165 weakly suppresses
  14. L4:347 weakly excites
  15. L0:3014 weakly suppresses
  16. L2:132 weakly excites
  17. L1:2030 weakly suppresses
  18. L0:2100 weakly excites
  19. L0:1811 weakly excites
  20. L4:678 weakly excites 'have' after 'you' or 'to'
  21. L3:2103 weakly suppresses
  22. L0:2725 weakly suppresses
  23. L1:2444 weakly suppresses
  24. L0:2863 weakly suppresses

Feeds later layers

  1. L10:559 suppresses
  2. L7:1324 suppresses
  3. L7:2203 excites
  4. L10:1384 excites
  5. L13:1213 excites
  6. L11:981 suppresses
  7. L19:1615 suppresses
  8. L7:1280 suppresses
  9. L7:1944 excites
  10. L23:2163 suppresses
  11. L26:850 weakly suppresses
  12. L9:1890 weakly suppresses
  13. L22:2334 weakly suppresses
  14. L14:643 weakly suppresses
  15. L8:1351 weakly excites
  16. L18:666 weakly suppresses
  17. L8:919 weakly excites
  18. L9:654 weakly suppresses
  19. L7:2716 weakly excites
  20. L20:931 weakly suppresses the digit 6 inside years
  21. L21:2276 weakly excites
  22. L26:2072 weakly excites
  23. L23:2135 weakly excites
  24. L10:1008 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.

1 values between -1.22 and -1.161 values between -1.10 and -1.041 values between -0.98 and -0.923 values between -0.74 and -0.687 values between -0.50 and -0.447 values between -0.44 and -0.3823 values between -0.38 and -0.3165 values between -0.31 and -0.25162 values between -0.25 and -0.19335 values between -0.19 and -0.13580 values between -0.13 and -0.07792 values between -0.07 and -0.01874 values between -0.01 and 0.05535 values between 0.05 and 0.11299 values between 0.11 and 0.17137 values between 0.17 and 0.2345 values between 0.23 and 0.2920 values between 0.29 and 0.357 values between 0.35 and 0.413 values between 0.41 and 0.473 values between 0.47 and 0.542 values between 0.54 and 0.602 values between 0.60 and 0.661 values between 0.66 and 0.721 values between 0.78 and 0.841 values between 1.08 and 1.141 values between 1.14 and 1.20offnegativepositiveoften

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. 烷
  2. ipse
  3. na
  4. ונה
  5. egal
  6. ⏎
  7. ⏎ ⏎
  8. 科室
  9. pane
  10. WiFi

Suppresses

  1. [value
  2. ehr
  3. issy
  4. 직
  5. -repeat
  6. Enough
  7. kehr
  8. cropped
  9. veau
  10. bem