Neuron Explorer

Qwen3-0.6B

indefinite 'a' or 'an' before a noun

A neuron in layer 14 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 responds to the small words "a" and "an" right before a noun, especially after verbs or prepositions such as "onto a", "fill a" or "of a". Turning it up produced rambling text that did not clearly echo this pattern.

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

    substance, usually a medication or bioactive agent, transdermally by repulsive electromotive force, through the skin. A small electric current is applied to an iontophoretic chamber placed on the skin, containing a charged active agent

  2. #2 peak

    Hadid surprised the crowd. The audience shock-factor came from the garment that Bella Hadid wore, which was a spray-on dress. Hadid walked slowly onto a platform in the middle of the runway. Here she was sprayed by two technicians with

  3. #3 peak

    10,000 people — most of them black — homeless.⏎But in his new book, Pulitzer Prize winning author David Zucchino re-examines a white attack on another black community — in Wilmington, North Carolina — that in many

  4. #4 peak

    rough shape,” Sam Turner, director of archaeology at the St. Augustine Lighthouse and Museum, said of the button.⏎Even so, the top part of a crown can be seen on the button and similar crowns are found on Royal Provincial

  5. #5 peak

    power, so it could be used in remote regions where water purity is a concern due to lack of centralized treatment. The user would load the right cartridge, fill a reservoir with the water to be tested, and run the punch card through. This

  6. #6 peak

    to them.⏎Current Event April 16, 2019⏎The Grand Canyon National Park recently celebrated its 100th birthday. A park ranger there created a “pop-up project,” placing an old typewriter on an

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 think about the role of a system, and then I need to be able to think about the roles, and then I need to be able to respond to the roles, and then the roles should be connected to

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

    economy.⏎In order to find a solution to the current financial situation, it is necessary to understand the actual problem. It is insane for one to expect to solve a problem with incorrect information. Therefore we need to end some myths regarding the budget.⏎

  2. #2 peak

    departments, universities, etc.) having jurisdiction over disposal of sewage, industrial wastes, stormwater or other wastes. This includes special districts under state law, such as a sewer district; flood control district, drainage districts or similar entity; an Indian tribe

  3. #3 peak

    . (Celsius)||-65|⏎|Max. Temp. (Celsius)||165|⏎There are no reviews yet.<|endoftext|>Talk about doing something in the blink of an eye.⏎Google wants to take that phrase to a new

  4. #4 peak

    to take risks, and was hard headed once he had made up his mind on something. At the time it was unclear how much oil was left in the ground 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. L11:331 strongly suppresses
  2. L11:875 strongly excites
  3. L10:1377 strongly excites
  4. L4:49 strongly excites
  5. L10:120 strongly excites
  6. L13:1234 strongly excites
  7. L9:662 strongly excites
  8. L10:1162 strongly suppresses
  9. L4:73 excites
  10. L13:824 excites
  11. L11:1168 suppresses
  12. L2:205 suppresses
  13. L6:426 excites
  14. L4:740 excites
  15. L5:225 suppresses
  16. L5:705 suppresses
  17. L5:153 excites
  18. L9:2198 suppresses
  19. L12:1868 suppresses
  20. L11:2859 suppresses
  21. L11:1245 excites
  22. L7:155 suppresses
  23. L9:24 suppresses "the" before a named organisation or title
  24. L12:966 suppresses

Feeds later layers

  1. L18:2630 excites
  2. L15:1888 excites
  3. L17:2190 suppresses 'the' starting an object phrase
  4. L18:1547 suppresses
  5. L15:3031 excites
  6. L16:2248 excites
  7. L17:1232 suppresses
  8. L17:2288 excites
  9. L17:1816 suppresses
  10. L17:2011 suppresses
  11. L19:1543 suppresses
  12. L17:1652 excites
  13. L17:2202 excites
  14. L16:2861 suppresses
  15. L16:2062 suppresses "other" and contrast words
  16. L15:2402 suppresses
  17. L20:1983 suppresses
  18. L15:2571 weakly suppresses
  19. L26:2817 weakly excites
  20. L15:1849 weakly suppresses
  21. L16:2466 weakly suppresses
  22. L17:188 weakly excites 'a' before a noun phrase
  23. L16:1212 weakly suppresses
  24. L18:1449 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 -2.65 and -2.502 values between -2.18 and -2.022 values between -2.02 and -1.861 values between -1.70 and -1.542 values between -1.38 and -1.225 values between -1.22 and -1.0710 values between -1.07 and -0.917 values between -0.91 and -0.7516 values between -0.75 and -0.5949 values between -0.59 and -0.43179 values between -0.43 and -0.27509 values between -0.27 and -0.111795 values between -0.11 and 0.05989 values between 0.05 and 0.21252 values between 0.21 and 0.3741 values between 0.37 and 0.5215 values between 0.52 and 0.6813 values between 0.68 and 0.845 values between 0.84 and 1.005 values between 1.00 and 1.161 values between 1.16 and 1.324 values between 1.32 and 1.481 values between 1.48 and 1.641 values between 1.96 and 2.111 values between 2.11 and 2.271 values between 2.59 and 2.751 values between 3.54 and 3.70offnegativepositiveoften

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. 有
  2. odo
  3. thes
  4. 有不同的
  5. 常见的
  6. Open
  7. 好评
  8. 新闻记者
  9. 国立
  10. ODO

Suppresses

  1. ��
  2. ROLS
  3. ::$
  4. ";}⏎
  5. $"
  6. RuleContext
  7. KANJI
  8. 陛下
  9. stuff
  10. _parms