Neuron Explorer

Qwen3-0.6B

'least' in 'at least'

A neuron in layer 5 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 lights up on the word 'least' when it follows 'at' in the phrase 'at least'. Turning it up or down made the model wander into unrelated text.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens an email to the maker with the neuron already filled in).

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

    of your dreams.⏎Different industry sectors demand different employability skills – personal as 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

  2. #2 peak

    ancient DNA from old bones, are revealing some of that lost history.⏎We now suspect, for example, that the bacterium has been infecting people since at least the Neolithic period.⏎Last year, scientists revealed that a Stone Age hunter-g

  3. #3 peak

    Others feel it too, and send you back more of the same.⏎SO…if you send out a sincere wish to help each other get through this or at least agree to disagree, people feel that too, and it can shift their state.

  4. #4 peak

    no way a<|endoftext|>If you’ve been around these few months, chances are good that you at least have a passing knowledge of what cryptocurrencies are. You may even have heard of names

  5. #5 peak

    via hands and surfaces*. But as there is no evidence that I know of that supports the fomite route for COVID-19, and we now have at least some (relatively weak) evidence against it, then it is surprising how much

  6. #6 peak

    . The tribade was the most common (vulgar) lesbian in European texts for many centuries. ?Tribade? occurs in English texts from at least as early as 1601 to at least as late as the mid

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: the other people are busy with their hands, but with the limitations of time and creativity. Oh, I don't have time for this. It's a very common problem. Maybe the people are just getting confused, so they need to get

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

    the direction of which is reversed at regular intervals or cycles. Electricity transmission networks use AC because voltage can be controlled with relative ease.⏎Amorphous Silicon — A thin-film, silicon photovoltaic cell having no crystalline structure. Manufactured

  2. #2 peak

    In practical terms, the exact meaning of "surface" will vary according to the measurement method used. A satellite infrared radiometer indirectly measures the temperature of a very thin layer (about 10 micrometres thick) or skin of the

  3. #3 peak

    uses in everyday life is an intriguing work of art combined with science. Fiber optics has been fabricated from materials that transmit light and are made from a bundle of very thin glass or plastic fibers enclosed in a tube. One end is at a source of

  4. #4 peak

    ub that grows up to 900 mm, but some forms may reach a height of up to 2 m. It has very distinctive, long, thin, needle-like leaves that curve upwards, giving the plants the appearance of small pine

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. L4:2624 suppresses
  2. L3:2794 excites
  3. L4:203 excites
  4. L4:1795 weakly excites "at least" phrase
  5. L4:1461 weakly excites
  6. L4:1115 weakly suppresses
  7. L4:2941 weakly excites
  8. L2:1899 weakly excites
  9. L1:2166 weakly suppresses
  10. L0:1979 weakly suppresses
  11. L0:1922 weakly suppresses
  12. L2:2565 weakly excites
  13. L2:1424 weakly excites
  14. L4:1779 weakly suppresses
  15. L2:1106 weakly excites
  16. L1:592 weakly excites
  17. L3:2529 weakly suppresses
  18. L3:2284 weakly suppresses
  19. L3:649 weakly suppresses
  20. L2:1219 weakly suppresses
  21. L4:2860 weakly suppresses
  22. L3:2746 weakly excites
  23. L4:1177 weakly excites
  24. L4:694 weakly suppresses

Feeds later layers

  1. L8:1736 excites
  2. L7:2434 excites
  3. L15:3063 weakly excites
  4. L18:2965 weakly excites
  5. L22:1612 weakly excites
  6. L8:1050 weakly suppresses
  7. L11:1004 weakly excites
  8. L7:1155 weakly suppresses
  9. L9:563 weakly excites
  10. L6:678 weakly suppresses
  11. L24:442 weakly excites
  12. L16:2836 weakly excites
  13. L16:885 weakly excites
  14. L16:1853 weakly excites
  15. L8:1914 weakly suppresses
  16. L10:1636 weakly excites
  17. L25:2468 weakly suppresses
  18. L22:2571 weakly suppresses
  19. L10:1006 weakly suppresses
  20. L19:1862 weakly excites
  21. L11:472 weakly excites
  22. L15:1916 weakly excites
  23. L10:476 weakly excites
  24. L14:2149 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 -2.25 and -2.132 values between -1.79 and -1.671 values between -1.67 and -1.561 values between -1.45 and -1.331 values between -1.33 and -1.221 values between -1.10 and -0.991 values between -0.99 and -0.871 values between -0.87 and -0.762 values between -0.76 and -0.646 values between -0.64 and -0.5312 values between -0.53 and -0.4162 values between -0.41 and -0.30246 values between -0.30 and -0.19887 values between -0.19 and -0.071797 values between -0.07 and 0.04698 values between 0.04 and 0.16148 values between 0.16 and 0.2726 values between 0.27 and 0.393 values between 0.39 and 0.501 values between 0.50 and 0.623 values between 0.62 and 0.734 values between 0.73 and 0.851 values between 1.07 and 1.191 values between 1.65 and 1.761 values between 2.11 and 2.221 values between 2.22 and 2.33offnegativepositiveoften

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. ators
  2. gow
  3. Incre
  4. 蕉
  5. ious
  6. ackle
  7. 产出
  8. binations
  9. BR
  10. ments

Suppresses

  1. .unique
  2. pragma
  3. mpz
  4. AVOR
  5. 风口
  6. ENARIO
  7. seize
  8. phoon
  9. liğinde
  10. jeta