Neuron Explorer

Qwen3-0.6B

the word 'following' after 'the'

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 'following' in phrases like 'which of the following' or 'read the following', the kind of wording used in quizzes and instructions. When it was turned up, the model's text drifted into repeated phrases rather than anything about quizzes.

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

    options contract has the following properties or attributes:⏎- Expiration Date⏎- Symbol or Underlying⏎-

  2. #2 peak

    -choice question for which there is no single correct answer but for which there are perhaps more justifiable answers and less justifiable answers. Something like “Which of the following motivations best explains so-and-so’s actions in such-and-such novel?” Instead

  3. #3 peak

    <|endoftext|>Recall that the conjugate base of an acid is simply the compound formed when an acid loses a hydronium ion (H+).⏎Which the following represent conjugate acid–base pair? For the pair that is not conjugate

  4. #4 peak

    :37⏎Exercise7. Read the following sentences, underline the main verb and state the verb: Active or Passive.⏎1

  5. #5 peak

    ⏎A. Modern Model⏎B. Classful Model⏎C. Classless Model⏎D. Heterogeneous Model⏎6-5. Which of the following is correct in CIDR?⏎A. Class A includes Class B network⏎B

  6. #6 peak

    . 4 bits⏎B. 8 bits⏎C. 16 bits⏎D. 32 bits⏎6-7. Which of the following is reliable communication?⏎D. All of them⏎6-8. What is

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 have been thinking about lately, and I have been thinking about lately. So I am thinking about lately. So I am thinking about lately. So I am thinking about lately. I have been thinking about lately. So I am thinking about

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

    5 eroding from a bank at approximately⏎25 cm below the current terrain⏎surface (see in-situ photo below).⏎Its front surface,⏎

  2. #2 peak

    one ocean sitting below the familiar Ice I found on Earth and on top of different high-pressure ices.⏎

  3. #3 peak

    range from shallow (2” to 3” below the surface) to deep bands at 6” or lower. Deep applications tend to

  4. #4 peak

    facsimile reprint of a 1901 variation by means of the Macmill<|endoftext|>This question seems like such a common occurrence. It most always follows the realization that we have a visual impairment. Honestly, it IS a fair question.

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. L12:1289 weakly excites
  2. L15:585 weakly suppresses
  3. L17:908 weakly excites
  4. L11:1267 weakly suppresses
  5. L11:2552 weakly excites
  6. L22:780 weakly suppresses
  7. L14:2266 weakly excites
  8. L20:2017 weakly excites
  9. L6:487 weakly excites
  10. L15:721 weakly excites
  11. L6:539 weakly excites
  12. L23:2293 weakly suppresses
  13. L15:2582 weakly excites
  14. L17:1965 weakly suppresses
  15. L16:1979 weakly excites
  16. L14:1701 weakly excites
  17. L8:2999 weakly suppresses
  18. L14:2539 weakly suppresses
  19. L20:1532 weakly excites
  20. L26:2333 weakly excites
  21. L18:2270 weakly suppresses
  22. L22:365 weakly suppresses
  23. L26:2478 weakly suppresses
  24. L25:1602 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.

2 values between -1.28 and -1.131 values between -0.97 and -0.822 values between -0.66 and -0.514 values between -0.51 and -0.3545 values between -0.35 and -0.20660 values between -0.20 and -0.042864 values between -0.04 and 0.11326 values between 0.11 and 0.273 values between 0.27 and 0.431 values between 4.77 and 4.93offnegativepositiveoften

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. yk
  2. yne
  3. imens
  4. 的操作
  5. ysize
  6. ayscale
  7. enso
  8. nop
  9. implement
  10. iphertext

Suppresses

  1. solitude
  2. 决
  3. libero
  4. treffen
  5. _None
  6. 慰
  7. 流出
  8. 流水
  9. الدنيا
  10. ance