Neuron Explorer

Qwen3-0.6B

'of' in 'members of the family'

A neuron in layer 7 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 'of' when it comes after 'member' or 'members', as in 'members of the family' or 'a member of the snapdragon family'. It tends to be negative on words like 'attention' or 'respond'. Turning it up or down changed the model's text in ways that did not clearly relate to families or membership.

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

    (Buckminster-Fuller, 1969)⏎The buckyball is the simplest of the carbon structures known as fullerenes. Members of the fullerene family are a major subject of nanotechnology research. 3-D

  2. #2 peak

    pretty flowers," he says.⏎Yellow toadflax, sometimes called butter and eggs, was actually introduced as an ornamental plant. "It's a member of the snapdragon family that people liked because it was pretty. Now it has escaped

  3. #3 peak

    A universal element of a functor is an element , where is some object of , which exhibits representability of via the Yoneda lemma. That is, any element induces, in natural bijective fashion, a natural transformation⏎and is universal if

  4. #4 peak

    fungus associated with Xyleborus glabratus has also been recovered from pond spice, indicating that this plant may also be a host.⏎All plants are members of the family Lauraceae and are important to wildlife as browse and fruit plants.

  5. #5 peak

    make art? Send us your ideas!<|endoftext|>Tobacco mosaic virus (TMV) is an RNA virus that infects plants, especially tobacco and other members of the family Sol

  6. #6 peak

    of Edinburgh.⏎DePolo was the lead writer of a report on the study. The findings were published in the journal PLOS ONE.⏎The most famous member of the stegosaurs was Stegosaurus, which lived late in the Jurassic Period

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 need to be able to remember it. I need to have that information. So, if that is the case, then that is the best for me. If I can recall that, and that is the best for me. If I

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

    Festo. For this reason, technical training and further education is subject to enormous change.⏎Learning trends in basic and advanced training⏎Many studies show that people's attention span has fallen sharply in recent years. This is

  2. #2 peak

    healthcare providers who are not familiar with the condition and don’t know what to look for. You may want to consider getting a second opinion if your symptoms do not respond.<|endoftext|>It is impossible to think of the Guatemalan, Mexican and M

  3. #3 peak

    belief among some teachers that students’ constant use of digital technology is hampering their attention spans and ability to persevere in the face of challenging tasks, according to two

  4. #4 peak

    't be counted.⏎But folks (like me) interested in understand how students learn best often distill the major patterns into four categories of learning style:⏎- Visual learners, who learn best by seeing a concept illustrated.⏎- Auditory learners, who

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. L5:759 suppresses
  2. L2:2926 weakly excites
  3. L6:2829 weakly suppresses
  4. L6:1951 weakly excites
  5. L4:1388 weakly excites
  6. L6:728 weakly suppresses
  7. L5:215 weakly excites
  8. L0:1693 weakly suppresses
  9. L6:1097 weakly excites
  10. L6:1341 weakly excites
  11. L2:1809 weakly suppresses
  12. L4:2859 weakly excites
  13. L5:3066 weakly excites
  14. L1:146 weakly excites
  15. L1:694 weakly suppresses
  16. L6:2520 weakly excites
  17. L3:2481 weakly suppresses
  18. L3:3002 weakly excites
  19. L6:2871 weakly suppresses
  20. L1:2746 weakly suppresses
  21. L5:1193 weakly suppresses
  22. L4:1309 weakly excites
  23. L4:987 weakly excites
  24. L2:2743 weakly suppresses

Feeds later layers

  1. L9:1409 excites
  2. L18:2121 weakly suppresses
  3. L14:1901 weakly excites
  4. L9:2265 weakly suppresses
  5. L22:1139 weakly suppresses
  6. L11:1683 weakly excites
  7. L10:2572 weakly suppresses
  8. L10:2200 weakly excites
  9. L8:879 weakly suppresses
  10. L13:2414 weakly suppresses
  11. L15:2096 weakly excites
  12. L16:2079 weakly excites
  13. L22:795 weakly suppresses
  14. L12:339 weakly suppresses
  15. L21:2609 weakly excites
  16. L12:1259 weakly excites
  17. L13:2385 weakly excites
  18. L9:1433 weakly excites
  19. L9:1738 weakly suppresses
  20. L13:2065 weakly excites
  21. L16:2585 weakly suppresses
  22. L18:1734 weakly excites
  23. L13:1782 weakly suppresses
  24. L20:2643 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 -3.02 and -2.911 values between -2.91 and -2.801 values between -2.80 and -2.692 values between -1.48 and -1.371 values between -1.26 and -1.151 values between -1.15 and -1.042 values between -1.04 and -0.933 values between -0.93 and -0.822 values between -0.71 and -0.6011 values between -0.60 and -0.4918 values between -0.49 and -0.3872 values between -0.38 and -0.27299 values between -0.27 and -0.16808 values between -0.16 and -0.051514 values between -0.05 and 0.06812 values between 0.06 and 0.17272 values between 0.17 and 0.2856 values between 0.28 and 0.3915 values between 0.39 and 0.506 values between 0.50 and 0.612 values between 0.61 and 0.722 values between 0.72 and 0.844 values between 0.84 and 0.951 values between 1.06 and 1.171 values between 1.17 and 1.281 values between 1.28 and 1.39offnegativepositiveoften

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. ->$
  2. 道德
  3. rong
  4. DIRECTORY
  5. anje
  6. ylie
  7. age
  8. [D
  9. lø
  10. ena

Suppresses

  1. Institutes
  2. -report
  3. informations
  4. иру
  5. bite
  6. 省教育厅
  7. อน
  8. -news
  9. _news
  10. reluct