Neuron Explorer

Qwen3-0.6B

'the' after 'lack' or 'have'

A neuron in layer 3 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 'the' when it comes right after words like 'lack', 'have' or 'possess', where a noun such as knowledge or resources is expected next. Turning it up made the model write more ordinary, general text with no clear theme.

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

    knowledge necessary to make informed decisions and take responsibility for their own financial well-being. Faced with an array of complex financial services and sophisticated products, many graduates lack the knowledge and skills to make rational, informed decisions on the use of their money and

  2. #2 peak

    the most-common challenges in security planning⏎- Some state policies require, without providing adequate implementation funding, that LEAs adopt specific measures, and many LEAs lack the resources and expertise to prepare competitive applications.⏎- The lack of conclusive research evidence about

  3. #3 peak

    pest, the bronze birch borer. River birches are less susceptible to the borers than are paper birch trees. And though river birches lack the classic white bark, their curly, cinnamon-colored bark has its own charm.⏎De

  4. #4 peak

    Jewish friends leshana tova (happy New Year), to send greeting cards, and perhaps plant trees in Israel in their honor.⏎Although the high holidays lack the merriment of Purim, the gift giving of Hanukkah, and

  5. #5 peak

    . There were and still are efforts to address the current challenges to space security but the instruments resulting from, or proposed by, those efforts lack the same legal force as the original, constitutive legal instruments; they are somewhat vague

  6. #6 peak

    Eventually the disease will cause plants to defoliate and die.⏎If a plant is infected by the pathogen, it cannot be cured. Homeowners who have the disease should remove and destroy all infected plants. Nearby uninfected impatiens

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 most recent, and most recent, in the book of the story of the city of the world, I have been told about the recent and reclusive, in the book of the world, I have been to the city of the world

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 its guardian Izad (god), who was considered one of the greatest Iranian deities in the “Zarwani” beliefs, annually on Bahman 22 (February 11). Other names for this feast are “

  2. #2 peak

    out of date, and any more recent senses may be completely missing.⏎- The inedible parts of a grain-producing plant.⏎- To separate out the chaff, early cultures tossed baskets of grain into the air and let the wind blow away

  3. #3 peak

    Presence of Christ⏎By Chuck Collins⏎Center for Reformation Anglicanism⏎Transubstantiation became the official doctrine of the Roman Catholic Church at the Fourth Lateran

  4. #4 peak

    wine of Holy Communion change into the body, blood, and soul of our Lord when magic words are spoken over them by a fancy-dressed priest. Transubstantiation and its Anglican clone are excuses to worship Jesus in the bread and

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. L1:1029 weakly excites
  2. L2:115 weakly excites
  3. L0:1301 weakly suppresses
  4. L1:323 weakly excites
  5. L2:2891 weakly excites
  6. L2:1166 weakly excites
  7. L1:388 weakly suppresses
  8. L1:1746 weakly excites
  9. L2:2347 weakly excites
  10. L2:2567 weakly suppresses
  11. L0:924 weakly suppresses
  12. L1:1477 weakly suppresses
  13. L2:2796 weakly suppresses
  14. L1:1464 weakly excites
  15. L1:702 weakly suppresses
  16. L2:111 weakly suppresses
  17. L2:293 weakly excites
  18. L2:2328 weakly suppresses
  19. L0:356 weakly suppresses
  20. L1:2115 weakly suppresses
  21. L1:2957 weakly excites
  22. L2:386 weakly excites
  23. L1:2683 weakly excites
  24. L0:178 weakly suppresses

Feeds later layers

  1. L11:2529 suppresses 'here' in 'read more here' links
  2. L9:1959 weakly excites
  3. L6:384 weakly excites
  4. L6:2556 weakly suppresses
  5. L7:171 weakly suppresses
  6. L6:2412 weakly excites
  7. L12:2805 weakly excites
  8. L6:2823 weakly excites
  9. L7:1758 weakly suppresses
  10. L11:1972 weakly suppresses
  11. L22:1980 weakly suppresses
  12. L23:1973 weakly excites
  13. L13:2803 weakly suppresses
  14. L23:2666 weakly excites
  15. L21:2557 weakly excites
  16. L17:3050 weakly suppresses
  17. L20:1060 weakly suppresses
  18. L15:1602 weakly excites
  19. L22:1337 weakly excites
  20. L16:1773 weakly suppresses
  21. L22:2136 weakly excites
  22. L8:2704 weakly suppresses
  23. L10:2754 weakly suppresses
  24. L6:568 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 -1.24 and -1.081 values between -0.92 and -0.761 values between -0.76 and -0.602 values between -0.60 and -0.4528 values between -0.45 and -0.29353 values between -0.29 and -0.132195 values between -0.13 and 0.031131 values between 0.03 and 0.19164 values between 0.19 and 0.3515 values between 0.35 and 0.515 values between 0.51 and 0.663 values between 0.66 and 0.821 values between 0.82 and 0.981 values between 0.98 and 1.142 values between 1.14 and 1.302 values between 1.61 and 1.771 values between 1.77 and 1.931 values between 1.93 and 2.091 values between 4.94 and 5.10offnegativepositiveoften

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. leep
  2. morning
  3. omon
  4. plex
  5. OfFile
  6. cost
  7. �
  8. headache
  9. cona
  10. contin

Suppresses

  1. ibase
  2. rawid
  3. entin
  4. ’y
  5. ícul
  6. !」
  7. ース
  8. .dest
  9. .det
  10. nds