Neuron Explorer

Qwen3-0.6B

sentence-starting 'This' at text start

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 reacts to the word 'This' when it begins a sentence or fragment, especially at the very start of a snippet. Turning it up did not produce a clear shift in the writing.

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

    . This is⏎Now an -simplex in the comma category , which is an element

  2. #2 peak

    This is a question that many consumers have when it comes to choosing plastic bottles for their

  3. #3 peak

    This is a sometimes hypothetical pre-shoot narrative document describing what happens in the film from

  4. #4 peak

    This will keep them in their new position until bones grow around the teeth to hold them

  5. #5 peak

    This can help develop a mighty plan that can make farms healthy enough to not require the

  6. #6 peak

    This is quite simple. First, compile (but don't link) each of your

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 trying to understand the problem, and I have been thinking about it for a while. I have been thinking about it, and I have been thinking about it for a while. I have been thinking about it, and I have

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

    of a meal at a restaurant? Usually you get your leftovers in a foil container with a cardboard lid⏎- styrofoam containers – again you might get this from a restaurant for leftovers or as a takeout container from a fast food place

  2. #2 peak

    Zuck, pp. 20). F. Biblical Theology "Biblical theology is the study of divine revelation as File Size: KB.⏎Get this from a library! Principles of biblical interpretation: (sacred hermene

  3. #3 peak

    get this book, download the free Human Anatomy and Physiology Pdf right now from our website.

  4. #4 peak

    (e.g., epiclesis, sanctus bells, the elevation, Mass of the Presanctified, etc.). Why is it important that we get this right? Because on our view of “real presence” in the sacrament hinges

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. L3:27 weakly suppresses
  2. L11:924 weakly excites
  3. L18:2752 weakly suppresses
  4. L9:1252 weakly suppresses
  5. L23:959 weakly suppresses
  6. L9:1624 weakly excites
  7. L7:163 weakly suppresses
  8. L3:1411 weakly excites
  9. L26:757 weakly suppresses
  10. L27:1536 weakly suppresses
  11. L22:1911 weakly suppresses
  12. L22:2625 weakly excites
  13. L4:579 weakly excites
  14. L16:2889 weakly suppresses
  15. L23:867 weakly suppresses
  16. L12:2906 weakly suppresses
  17. L16:1540 weakly excites
  18. L16:1993 weakly excites
  19. L3:1553 weakly suppresses
  20. L10:413 weakly suppresses
  21. L13:2021 weakly suppresses
  22. L7:954 weakly excites
  23. L18:2786 weakly excites
  24. L25:1849 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 -1.16 and -1.071 values between -0.98 and -0.884 values between -0.88 and -0.793 values between -0.79 and -0.704 values between -0.70 and -0.616 values between -0.61 and -0.525 values between -0.52 and -0.4311 values between -0.43 and -0.3425 values between -0.34 and -0.2595 values between -0.25 and -0.15428 values between -0.15 and -0.062328 values between -0.06 and 0.03773 values between 0.03 and 0.12139 values between 0.12 and 0.2127 values between 0.21 and 0.307 values between 0.30 and 0.392 values between 0.39 and 0.495 values between 0.49 and 0.586 values between 0.58 and 0.674 values between 0.67 and 0.768 values between 0.76 and 0.858 values between 0.85 and 0.947 values between 0.94 and 1.034 values between 1.03 and 1.131 values between 1.13 and 1.221 values between 2.13 and 2.221 values between 2.22 and 2.311 values between 2.31 and 2.403 values between 2.40 and 2.49offnegativepositiveoften

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. denom
  2. then
  3. oks
  4. puis
  5. dent
  6. 玑
  7. 斯基
  8. hence
  9. 湜
  10. aku

Suppresses

  1. mentioned
  2. ши
  3. otify
  4. avigation
  5. 意见
  6. anning
  7. шин
  8. 该剧
  9. .addAction
  10. 的意见