Neuron Explorer

Qwen3-0.6B

inside all-caps abbreviations

A neuron in layer 0 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on a letter in the middle of a short capitalised code or abbreviation, such as the 'W' in BTW or the 'M' in CDM. Turning it up did not make the writing about any single topic.

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

    BTW € 125,00<|endoftext|>Hell Maximillian (172

  2. #2 peak

    the Space Science Institute in Boulder, Colo.⏎For more information about the Cassini-Huygens mission visit http://saturn.jpl.nasa.gov/home/index.cfm. The Cassini imaging team homepage is at http://ciclops.org.

  3. #3 peak

    x 638 mm; watermark: Atlas holding the celestial spheres; slightly frayed and darkened edges, else in fine condition.⏎Incl. BTW € 151,25⏎Excl.

  4. #4 peak

    1,700.<|endoftext|>Risk assessment for construction⏎The Construction (Design and Management) Regulations (CDM Regulations) are intended to ensure that health and safety issues are properly considered during a

  5. #5 peak

    power point. Figure 3 shows the operating range for PWM controllers.⏎Figure 2: PWM Charge Controller⏎Figure 3: Power Curve for a PPV Panel⏎MPPT Charge Controllers⏎MPPT or the Maximum Power Point Tracking provides

  6. #6 peak

    CPSC. Their 2011 Fireworks Annual Report noted that children younger than

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 make the next time to be in the game of the game of the world. " I need to do something, I need to do the next. " So, I need to do the next. " So, I

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

    . You can export a word list with a word frequency count to import into other visualization tools. http://www.antlab.sci.waseda.ac.jp/software.html⏎Voyant Tools: Voyant Tools is a free web based suite

  2. #2 peak

    & Co. (04/01/2000), and Others|⏎The novel opens in form of a letter by Wiliam Crimsworth to his school friend, describing his life after he left the school. The first

  3. #3 peak

    transatlantic networks that wove the exiles of African descent, the gens de couleur, together across the Atlantic. Exploring the careers of Joseph and Sévère Courtois provides a window

  4. #4 peak

    vère penned the letter urging his brother to support his universal liberation enterprise, Joseph had just come back from fighting in the Napoleonic wars in Europe. Sévère had participated in multiple revolutionary coups and moved from New Orleans to Cartag

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. L2:50 suppresses
  2. L1:1031 suppresses
  3. L4:1595 weakly suppresses
  4. L6:1854 weakly suppresses
  5. L12:163 weakly excites
  6. L1:332 weakly suppresses
  7. L19:1584 weakly suppresses
  8. L2:2174 weakly suppresses
  9. L1:156 weakly suppresses
  10. L13:1643 weakly suppresses
  11. L24:2826 weakly suppresses
  12. L1:1707 weakly suppresses
  13. L17:419 weakly suppresses
  14. L3:189 weakly suppresses
  15. L10:1620 weakly excites
  16. L1:1753 weakly suppresses
  17. L1:2450 weakly suppresses
  18. L5:15 weakly suppresses
  19. L19:342 weakly excites
  20. L3:1488 weakly suppresses
  21. L24:2621 weakly suppresses
  22. L25:1486 weakly suppresses
  23. L1:3055 weakly suppresses
  24. L22:2814 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.

6 values between -0.29 and -0.247 values between -0.24 and -0.1959 values between -0.19 and -0.14238 values between -0.14 and -0.09803 values between -0.09 and -0.041566 values between -0.04 and 0.01882 values between 0.01 and 0.06279 values between 0.06 and 0.1155 values between 0.11 and 0.167 values between 0.16 and 0.211 values between 0.21 and 0.261 values between 0.57 and 0.621 values between 0.72 and 0.772 values between 1.02 and 1.071 values between 1.67 and 1.72offnegativepositiveoften

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. następ
  2. şek
  3. ôte
  4. _note
  5. 它
  6. anguage
  7. it
  8. dön
  9. ingu
  10. arn

Suppresses

  1. 网讯
  2. 大的
  3. ístico
  4. 米尔
  5. allas
  6. リー
  7. 闭
  8. 个项目
  9. isons
  10. misplaced