Neuron Explorer

Qwen3-0.6B

"at" ending a phrase

A neuron in layer 19 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 "at" in fixed phrases like "not at all", "at a time", "at the same time" and "late at night". When turned up, the model fell into loops of "at the end of the day".

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

    the water and waste in the system to flow smoothly out to the sewer or septic tank. If there were no vent, the system would drain slowly or not at all, not unlike a water-filled straw when you seal one end with your finger

  2. #2 peak

    Roughly a third of the people are poor, with 23 percent living “in misery, on one meal a day and not a very nourishing meal at that.” The rich, on the other hand, are very rich indeed. “

  3. #3 peak

    place cool things for him to explore.⏎Still, kids do need to learn the word “no.” You want to reserve “no” for only a few things at that age–activities that might

  4. #4 peak

    it difficult to say more than just a few words before pausing to breathe.⏎Weight Training Exercises⏎In weight-training exercises, you generally focus on one muscular group at a time, doing enough repetitions of the exercise to tire the muscles. The Centers

  5. #5 peak

    is easy to exceed a healthy daily caloric limit when eating fast foods. Eating several smaller meals throughout the day will help you to avoid this type of eating late at night.⏎<|endoftext|>Swept source optical coherence tomography, also known as swept

  6. #6 peak

    a broad theme that in order to write a profound essay, you need to narrow your topic as much as possible. Otherwise, you will write about everything and nothing at the same time. Think thoroughly what you are asked to do. Does it have

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: at the at a certain at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at at

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

    or laptop you will need to have Adobe Digital Editions installed. It is a free software. We also strongly recommend that you sign up for an AdobeID at the Adobe website. For more details please see FAQ 1&2. To view

  2. #2 peak

    or laptop you will need to have Adobe Digital Editions installed. It is a free software. We also strongly recommend that you sign up for an AdobeID at the Adobe website. For more details please see FAQ 1&2. To view

  3. #3 peak

    theological catch-phrase seems to have wide acceptance currently: We are called to be servants. Scriptures seem to invite that identity and it makes sense: Love your neighbor as yourself. Serve others as Jesus served. Let the greatest among you be a servant

  4. #4 peak

    what exactly happened out there.⏎Thousands of people gathered on the streets of New York, patiently waiting for the arrival of RMS Carpathia…⏎This doesn’t come as a surprise, as the Titanic crash was a disaster of huge proportions back in the

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. L18:895 suppresses
  2. L4:430 suppresses
  3. L17:1325 excites
  4. L15:115 excites
  5. L15:129 suppresses
  6. L0:2473 suppresses
  7. L16:588 excites
  8. L16:76 excites
  9. L16:107 suppresses
  10. L17:166 excites
  11. L16:260 excites
  12. L15:78 excites
  13. L16:567 suppresses
  14. L1:21 excites
  15. L7:674 suppresses
  16. L15:122 suppresses
  17. L18:102 weakly suppresses
  18. L16:673 weakly excites
  19. L15:80 weakly suppresses
  20. L0:2837 weakly excites
  21. L8:2038 weakly suppresses
  22. L18:474 weakly excites
  23. L16:461 weakly excites
  24. L16:142 weakly excites

Feeds later layers

  1. L27:599 strongly suppresses
  2. L26:835 suppresses
  3. L23:1501 excites 'at' in idioms like 'at work'
  4. L22:764 excites
  5. L26:840 excites
  6. L24:856 suppresses
  7. L26:1210 suppresses
  8. L22:2713 excites
  9. L24:2924 weakly excites
  10. L25:501 weakly excites
  11. L23:2549 weakly excites
  12. L26:2537 weakly excites
  13. L21:1872 weakly suppresses
  14. L21:550 weakly suppresses
  15. L22:2227 weakly suppresses
  16. L22:1007 weakly excites
  17. L22:1493 weakly excites
  18. L24:1252 weakly suppresses
  19. L24:2968 weakly excites
  20. L24:748 weakly excites
  21. L25:2414 weakly excites
  22. L27:675 weakly suppresses
  23. L21:2012 weakly suppresses "to" before an infinitive or noun
  24. L23:1611 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.

1477 values between -2.34 and -0.472400 values between -0.47 and 1.416 values between 1.41 and 3.281 values between 3.28 and 5.163 values between 5.16 and 7.043 values between 7.04 and 8.911 values between 8.91 and 10.793 values between 10.79 and 12.661 values between 14.54 and 16.412 values between 16.41 and 18.292 values between 37.05 and 38.921 values between 42.68 and 44.552 values between 50.18 and 52.051 values between 61.43 and 63.311 values between 65.18 and 67.062 values between 68.94 and 70.812 values between 70.81 and 72.69offnegativepositiveoften

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. ypical
  2. tract
  3. 限り
  4. Coder
  5. least
  6. least
  7. ienza
  8. endphp
  9. emporary
  10. tracted

Suppresses

  1. at
  2. At
  3. At
  4. _at
  5. at
  6. "At
  7. atives
  8. .at
  9. [at
  10. -at