Neuron Explorer

Qwen3-0.6B

'etc' ending a list

A neuron in layer 17 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 'etc' when it closes a list of examples, like 'caries, etc' or 'fishing, etc'. Turning it up made the model fall into repeated 'like that' phrases, which does not clearly connect to lists.

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

    develop a definitive diagnosis, which allows the dental professional to rule out other possible causes of the pain (periodontal disease, caries, etc) and then implement an appropriate treatment plan to address the problem.⏎Dentin is

  2. #2 peak

    quick to blame low deer numbers due to drought, coyotes, poor habitat, etc., the plain and simple fact is that deer had an abundant food source available to

  3. #3 peak

    and lining the page, figuring out text length, divisions, etc.⏎Writing technology has made it easier for us to focus more on the text and

  4. #4 peak

    their race, religion, sex, or some other factor that is specified in the law. Unless there is a crime like assault, aggravated assault, attempted murder, etc. hate-crime laws generally do not apply.⏎Hate speech legislation criminalizes

  5. #5 peak

    onslaught of a second wave.⏎Major hotel chains, businesses focusing on labor-intensive work, service providers, etc. are among the major categories. It would include the employers of these categories in

  6. #6 peak

    extreme heat, entrained air, moisture, contamination by dirt and debris, inadvertent mixing with different oil, etc. - that degrade the integrity of the hydrocarbon base stock and deplete the

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: this is that this way like this this this this this this this this this this this this this this this this this this this like this this this this this this this this this like this this this this this this this like this this this this

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

    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

    fields,<|endoftext|>Bronze Age Odin⏎Since many want to be a leader it is easy to see Odin as the leader of the tribe. I doubt it always was so. Others maybe saw it as the leading aspect in man. In the Ritual

  3. #3 peak

    pressure for nervous writers.⏎Setup for Revealing Moment Exercise⏎First have students simply draw a line on a piece of paper. (It doesn't get any simpler than this). You may want to do this on the board along with them.⏎Then

  4. #4 peak

    , periodontitis, and possibly even obesity.⏎"People thought that asthma was caused by inhalation of allergens but this study shows that it may be more complicated than that - asthma may involve colonization of the airways by multiple bacteria," said study

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. L15:1930 suppresses
  2. L15:1237 suppresses
  3. L4:1352 suppresses
  4. L16:2861 excites
  5. L15:1995 weakly suppresses
  6. L16:942 weakly excites
  7. L14:1316 weakly excites
  8. L15:2683 weakly suppresses
  9. L16:666 weakly excites
  10. L6:1376 weakly excites
  11. L0:229 weakly excites
  12. L16:1991 weakly suppresses
  13. L6:2654 weakly suppresses
  14. L7:493 weakly suppresses 'this' pointing back to a topic
  15. L12:3027 weakly excites 'other' in 'and other ...' lists
  16. L14:1814 weakly suppresses
  17. L15:398 weakly excites
  18. L10:1603 weakly suppresses
  19. L6:773 weakly suppresses
  20. L10:2724 weakly excites
  21. L6:1425 weakly excites
  22. L16:2420 weakly excites
  23. L16:2692 weakly excites
  24. L16:1999 weakly excites

Feeds later layers

  1. L20:1922 suppresses
  2. L20:1704 suppresses
  3. L18:2938 suppresses
  4. L23:2015 suppresses
  5. L22:1469 suppresses
  6. L19:2918 suppresses
  7. L18:2923 weakly suppresses
  8. L21:492 weakly suppresses
  9. L18:313 weakly suppresses
  10. L18:769 weakly suppresses
  11. L20:42 weakly excites
  12. L25:769 weakly suppresses
  13. L23:932 weakly excites
  14. L21:1376 weakly suppresses
  15. L26:405 weakly suppresses
  16. L19:1875 weakly suppresses
  17. L19:1265 weakly suppresses
  18. L18:686 weakly excites
  19. L27:694 weakly suppresses
  20. L20:1766 weakly suppresses
  21. L20:2949 weakly suppresses
  22. L19:1124 weakly suppresses
  23. L19:1646 weakly suppresses
  24. L19:2425 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 -4.66 and -4.423 values between -1.52 and -1.281 values between -1.28 and -1.0415 values between -1.04 and -0.79110 values between -0.79 and -0.55448 values between -0.55 and -0.311377 values between -0.31 and -0.071441 values between -0.07 and 0.17410 values between 0.17 and 0.4167 values between 0.41 and 0.6611 values between 0.66 and 0.906 values between 0.90 and 1.145 values between 1.14 and 1.381 values between 1.38 and 1.626 values between 1.62 and 1.862 values between 2.10 and 2.352 values between 2.83 and 3.072 values between 4.76 and 5.00offnegativepositiveoften

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. бир
  2. '>"+
  3. obe
  4. yers
  5. opoly
  6. orgh
  7. 经验和
  8. ibName
  9. еб
  10. aversable

Suppresses

  1. 如此
  2. così
  3. 这样
  4. 然
  5. así
  6. such
  7. 那样
  8. thus
  9. 这样的话
  10. Such