Neuron Explorer

Qwen3-0.6B

second word of publication names

A neuron in layer 10 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron lights up on the later part of a well-known name, such as the 'ica' in Britannica, 'Science' after 'Popular', or 'Privacy' after 'Electronic'. It seems to predict the rest of a magazine, organisation or publication name. Turning it up gave mostly unrelated text, with one output mentioning the New York Times.

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

    Children were more vulnerable to rotavirus (p = 0.008, OR<|endoftext|>A Global Index of Sustainable Well-Being⏎Source: The New Economics Foundation⏎From the Executive Summary:⏎There is a growing global consensus that we need

  2. #2 peak

    marsat, but was withdrawn in 2008 and replaced by the broadband global area network (BGAN), a global satellite Internet network.⏎Techopedia explains Regional Broadband Global Area Network (

  3. #3 peak

    the ore is crushed and agglomerated prior to heap leaching. High grade ores and ores resistant to cyanide leaching at coarse particle⏎Gold processing Britannica.com⏎The mining of alluvial deposits and, later, lode or

  4. #4 peak

    's] records unless specifically permitted by the Act.” See Your Right to Federal Records: Questions and Answers on the Freedom of Information Act and the Privacy Act. Electronic Privacy Information Center, 1992.⏎The American Inquisition: Federalism

  5. #5 peak

    The early period, 1853–1930⏎Our editors will review what you’ve submitted and determine whether to revise the article.Join Britannica's Publishing Partner Program and our community of experts to gain a global audience for your

  6. #6 peak

    they need to escape, but then they are too full to bend over and sting.⏎• In “The American Frugal Housewife,” (the Better Homes and Gardens of its day) the author recommends using ear wax as lip balm.<|endoftext|>

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 can't be as specific as the time of my own age. So, what is the time of my own age? Maybe the time of my own age. So, how I am at the time of the age of the person.

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

    to Rapid City, fire weather meteorologists are watching conditions closely. And until we receive widespread, heavy moisture they'll be monitoring what is known as the Keetch-Byram Drought Index or KBDI.⏎It measures the amount of precipitation

  2. #2 peak

    of age or older completed a survey that included a food frequency questionnaire and cognitive assessment. Cognitive function was checked again during four assessments over 11 years using the Modified Mini-Mental State examination (3MS), which is graded on a 1

  3. #3 peak

    surely knew that this Act would shed light on the seditious acts of government officials. Curious.⏎Indeed, the Act itself, found in the Statutes at Large, 80 Stat. 383 stated:⏎"Except as

  4. #4 peak

    https://youtu.be/qlSxPouPCIM⏎The post 1929 Stock Market Crash and the Great Depression. first appeared on COMPLIANT PAPERS.⏎The post 1929 Stock Market Crash

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. L7:1847 excites
  2. L7:2571 suppresses
  3. L9:171 suppresses
  4. L9:450 excites
  5. L9:50 weakly suppresses
  6. L3:1124 weakly suppresses
  7. L6:1866 weakly excites
  8. L3:455 weakly suppresses unclear: mid-name word fragments
  9. L7:180 weakly excites
  10. L7:2229 weakly excites
  11. L1:1530 weakly suppresses
  12. L0:868 weakly excites
  13. L0:2010 weakly excites
  14. L7:2174 weakly suppresses
  15. L6:2164 weakly suppresses second half of multi-word proper names
  16. L9:904 weakly excites
  17. L8:114 weakly suppresses
  18. L3:169 weakly suppresses
  19. L5:26 weakly excites
  20. L4:1454 weakly excites
  21. L7:2492 weakly excites
  22. L9:1473 weakly suppresses
  23. L3:809 weakly excites
  24. L2:1824 weakly excites

Feeds later layers

  1. L12:3020 excites
  2. L13:1215 excites
  3. L16:2217 excites
  4. L18:2292 excites
  5. L13:2755 excites
  6. L19:1519 excites
  7. L21:2846 excites 'at' after a job title, before an institution
  8. L14:1677 excites
  9. L20:2813 excites
  10. L19:2135 excites
  11. L21:2850 excites
  12. L13:2165 excites
  13. L19:2411 excites
  14. L16:2166 excites
  15. L16:2208 excites
  16. L21:2520 excites
  17. L12:139 suppresses
  18. L12:756 excites
  19. L11:457 excites
  20. L15:2628 excites
  21. L11:1182 excites
  22. L22:2134 excites
  23. L13:450 suppresses
  24. L18:3040 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 -2.06 and -1.921 values between -1.63 and -1.491 values between -1.35 and -1.201 values between -1.20 and -1.062 values between -1.06 and -0.924 values between -0.77 and -0.637 values between -0.63 and -0.4928 values between -0.49 and -0.34190 values between -0.34 and -0.20837 values between -0.20 and -0.061819 values between -0.06 and 0.09756 values between 0.09 and 0.23187 values between 0.23 and 0.3831 values between 0.38 and 0.526 values between 0.52 and 0.6612 values between 0.66 and 0.813 values between 0.81 and 0.955 values between 0.95 and 1.093 values between 1.09 and 1.243 values between 1.24 and 1.382 values between 1.38 and 1.521 values between 1.67 and 1.811 values between 2.24 and 2.381 values between 2.38 and 2.531 values between 2.53 and 2.671 values between 2.67 and 2.811 values between 2.96 and 3.103 values between 3.53 and 3.67offnegativepositiveoften

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. 时报
  2. Sheet
  3. 报社
  4. #endregion
  5. 网站
  6. .microsoft
  7. Times
  8. chapel
  9. atoria
  10. Institute

Suppresses

  1. uant
  2. amiento
  3. uating
  4. ungan
  5. utches
  6. uate
  7. itious
  8. _own
  9. 환
  10. ung