Neuron Explorer

Qwen3-0.6B

"of" in fixed phrases like plain of

A neuron in layer 0 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 "of" in set phrases such as "Plain of Catania," "clear of fish," or "steer clear of." It is quiet on most other words. Turning it up made the model's writing wander into unrelated topics, so the link to the text is not clear from the steering.

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

    amounts of resources toward flood prevention and post-flood restoration. Consequently, no matter how hard the local population work, they remain the poorest of the poor.⏎The Tam Nông Hospital is an old hospital built in the early

  2. #2 peak

    almost constant state of activity. The fertile volcanic soils support extensive agriculture, with vineyards and orchards spread across the lower slopes of the mountain and the broad Plain of Catania to the south. Due to its history of recent activity and nearby population

  3. #3 peak

    island.⏎“Our livelihood depends on fishing, but in the past large ships would come in and sweep the whole ocean clear of fish. There was nothing left for us to eat,” Velasquez said.

  4. #4 peak

    ice made up of frozen nitrogen mixed with carbon monoxide and methane.⏎It covers an area four kilometers deep and a thousand kilometers wide in the Sputnik Plain of Pluto.⏎To understand the origins of this

  5. #5 peak

    the earthly to the spiritual world. The ritual decomposition is later followed by cremation and secondary burial.⏎On 6 July 2019, the Plain of

  6. #6 peak

    a farm located in the fields near the city, and there she became pregnant; the King decided to call the place "Pla del Bon Repos" ("Plain of good sleep"), a name that has been left to posterity and today is a

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 place of a group of people in a city in a month of the number of days and the number of days is the number of days in a month, the number of days, the number of days, the number of days, the

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

    angles formed by the cords on the disk—the sum of the forces and the equilibrium conditions. Provenance: Lorraine collections.<|endoftext|>

  2. #2 peak

    standard contribution is used when the marginal cost is using.⏎Sales Volume Variance Formula⏎In general, the formula of Sales Volume Variance is⏎Sales Volume Variance = (Actual units sold –

  3. #3 peak

    966.⏎Yet, though many of the panellists called it a “perfect” novel, “Wide Sargasso Sea” was not the sum of Rhys’ work. Her career spanned decades, from her early novels set

  4. #4 peak

    during that period than were youth in the city's general population.24 Youth in contact with a mental health system's services, however, are not the sum of a community's youth with mental health needs because many receive no services. The results

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

None: this is the first layer.

Feeds later layers

  1. L20:1963 weakly suppresses
  2. L24:3031 weakly excites
  3. L3:446 weakly suppresses
  4. L24:49 weakly excites
  5. L20:1390 weakly excites
  6. L4:2362 weakly excites
  7. L8:1069 weakly excites
  8. L13:1601 weakly suppresses
  9. L15:3033 weakly suppresses
  10. L13:2074 weakly suppresses
  11. L9:2786 weakly excites
  12. L16:2948 weakly excites
  13. L22:551 weakly suppresses
  14. L7:1515 weakly excites
  15. L15:1122 weakly excites
  16. L2:1547 weakly excites
  17. L9:45 weakly suppresses
  18. L4:2426 weakly suppresses
  19. L14:786 weakly excites
  20. L19:1270 weakly excites
  21. L9:2456 weakly suppresses
  22. L21:2141 weakly suppresses
  23. L13:2998 weakly suppresses
  24. L10:1996 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 -1.31 and -1.251 values between -1.19 and -1.121 values between -0.87 and -0.811 values between -0.74 and -0.683 values between -0.68 and -0.624 values between -0.62 and -0.553 values between -0.55 and -0.492 values between -0.49 and -0.436 values between -0.43 and -0.364 values between -0.36 and -0.305 values between -0.30 and -0.2419 values between -0.24 and -0.1772 values between -0.17 and -0.11413 values between -0.11 and -0.052258 values between -0.05 and 0.02838 values between 0.02 and 0.08180 values between 0.08 and 0.1433 values between 0.14 and 0.2124 values between 0.21 and 0.276 values between 0.27 and 0.348 values between 0.34 and 0.407 values between 0.40 and 0.466 values between 0.46 and 0.533 values between 0.53 and 0.594 values between 0.59 and 0.652 values between 0.72 and 0.781 values between 1.03 and 1.101 values between 1.10 and 1.162 values between 1.16 and 1.22offnegativepositiveoften

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. )--
  3. askell
  4. "),⏎⏎
  5. -Ta
  6. reetings
  7. """),⏎
  8. ),⏎⏎
  9. )⏎⏎
  10. ause

Suppresses

  1. endant
  2. قلب
  3. ctor
  4. ayar
  5. lạc
  6. atively
  7. ilog
  8. 亮丽
  9. 走出来
  10. вет