Neuron Explorer

Qwen3-0.6B

'this' after sentence-initial 'In'

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 fires on the word 'this' in the opening phrase 'In this guide' or 'In this article', which is a common way for web articles to start. It is one of the strongest and most consistent neurons in this set. Turning it up did not produce any clear theme in the model's replies.

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

    you.⏎In this guide, I’ll go through all the main elements pertaining to SSL certificates to provide

  2. #2 peak

    of interest to you.⏎In this guide, we’ll go over all of this in detail. We’ll explore the

  3. #3 peak

    of foreign policy.”⏎In this “age of great migration,” more societies are becoming like the United States, with

  4. #4 peak

    ’s heritage.⏎In this article, I’m going to look at the history of American culture and how that

  5. #5 peak

    Behind the Northern Lights⏎In this interactive session, Norwegian solar physicist Pål Brekke utilizes photos and video footage from

  6. #6 peak

    versus broadcasting nutrients is likely to become a much bigger conversation as Ontario works to reduce the impact farm phosphorous on the Great Lakes.⏎In this Corn School episode, Purdue University professor Tony Vyn offers insights on why he feels

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: how to make a circle of the day. I know that the circle is made by connecting the points. So, how to connect the points to make a circle. The points are the points of the day. The circle is the circle of

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

    gardenia.⏎Insecticides kill off the whitefly’s natural predators. These predators include other insects and

  2. #2 peak

    the continued loss of habitat in parks across the US, this is worth a read. The full article can be accessed here.⏎Tags: New York Times, Insect Population Decline<|endoftext|>First posted on Myth & Moor in 2015

  3. #3 peak

    -BEVS is a promising alternative strategy to produce the functional and thermostable reverse transcriptase.⏎All Science Journal Classification (ASJC) codes⏎- Insect Science<|endoftext|>An account of the religion of

  4. #4 peak

    fr.wikipedia.org⏎Note: you should have a Insecta.pro account to upload new topics and comments. Please, create an account or

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. L7:1220 excites
  2. L8:51 weakly excites
  3. L11:2894 weakly suppresses
  4. L15:194 weakly excites
  5. L12:2422 weakly excites
  6. L22:1127 weakly excites machine learning explanations, mid-sentence
  7. L2:2992 weakly suppresses
  8. L7:348 weakly excites
  9. L12:2316 weakly excites
  10. L11:1173 weakly excites
  11. L8:2299 weakly excites
  12. L12:1541 weakly suppresses
  13. L24:2376 weakly excites
  14. L3:2345 weakly suppresses
  15. L16:2787 weakly suppresses
  16. L9:1785 weakly excites
  17. L9:1210 weakly excites
  18. L13:2495 weakly suppresses
  19. L3:807 weakly suppresses comma inside dates and years
  20. L19:2466 weakly excites
  21. L24:2234 weakly suppresses
  22. L24:1901 weakly excites
  23. L6:1115 weakly suppresses
  24. L16:2073 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 -0.67 and -0.535 values between -0.53 and -0.3844 values between -0.38 and -0.24401 values between -0.24 and -0.092711 values between -0.09 and 0.06693 values between 0.06 and 0.2016 values between 0.20 and 0.353 values between 0.35 and 0.502 values between 0.50 and 0.643 values between 0.64 and 0.796 values between 0.79 and 0.9312 values between 0.93 and 1.083 values between 1.08 and 1.231 values between 1.23 and 1.371 values between 1.66 and 1.811 values between 1.96 and 2.101 values between 2.25 and 2.401 values between 2.40 and 2.541 values between 2.69 and 2.831 values between 4.73 and 4.881 values between 5.03 and 5.17offnegativepositiveoften

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. vido
  2. fer
  3. OMP
  4. Kimber
  5. 方式进行
  6. なもの
  7. ose
  8. 止
  9. away
  10. oir

Suppresses

  1. erializer
  2. icolor
  3. CharCode
  4. Endian
  5. iết
  6. >)
  7. Washer
  8. )")⏎⏎
  9. bitte
  10. bitten