Neuron Explorer

Qwen3-0.6B

'or' in either-or choices

A neuron in layer 11 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 'or' in phrases that offer two options, like 'prove or disprove' or 'publish or perish'. It is switched off by words like 'changed' and 'change'. Turning it up did not produce a clear theme in the model's text.

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

    th Report talked about how wrongful incarceration, conviction, and prosecution are defeating principles of justice. In order to curb this, the notion of ‘innocent until proven guilty

  2. #2 peak

    their] former glory.”⏎Supersymmetry and Q-balls are thus far only theoretical, although Cox asserts that he and the physicists at CERN will prove or disprove their existence by 2017. However, as Anthony Kauf

  3. #3 peak

    crisis are wide ranging, but typical center on the preference for “novel” findings in science and the pressure on investigators (especially new ones) to “publish or perish”. My favorite reason places the blame for the entire crisis on p-values.⏎

  4. #4 peak

    years of age, who had already failed to respond to at least two antipsychotic treatments, to participate in a 12-week, double-blind, randomized study – the most rigorous of clinical trial designs. After initial assessments, the patients

  5. #5 peak

    nation.⏎According to the Title I Director’s Conference (February 2003), “highly qualified” means that all teachers must have full State certification or have passed teacher licensing exam, and hold a license to teach, and that certification

  6. #6 peak

    sheep.⏎As such merino production inherently has the potential of being fully sustainable providing it is operated within the carrying capacity of the ecosystem.⏎They must operate, or be in the process of implementing, a grazing management strategy based on long term sustainability.⏎

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 this: I have been thinking about this: I have been thinking about this, and I will now share the following. The following is the content I have been thinking about: I have been thinking about this. 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

    “triggered” using a web bug. Each time it is requested, it checks to see if the current wiki page (containing the web bug) has changed and needs re-indexing.⏎On the first release containing the indexer<|endoftext|>Publications

  2. #2 peak

    things that background applications do, namely,⏎read its configuration files, go into the background, shut down when told to,⏎and restart in the case of a configuration change. Because it is an HTTP server,⏎it must be able to listen for incoming

  3. #3 peak

    loaded ? Or what to do if we would like to selectively update only parts of a page. For example only the stock item in an HTML TABLE whose rate has changed ?⏎Let's assume that we have a Java web/application server from which we want

  4. #4 peak

    devfsadm command. This daemon is started by the service management facility when a system is booted.⏎Because the devfsadmd daemon automatically detects device configuration changes generated by

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. L9:2920 suppresses
  2. L10:2051 suppresses
  3. L10:135 weakly excites 'or' in alternative requirements
  4. L8:1086 weakly suppresses
  5. L7:2974 weakly suppresses
  6. L6:1588 weakly suppresses
  7. L3:85 weakly excites
  8. L8:1667 weakly suppresses
  9. L10:14 weakly suppresses
  10. L9:1348 weakly excites
  11. L10:1208 weakly suppresses
  12. L5:2602 weakly excites
  13. L2:1766 weakly suppresses
  14. L3:1832 weakly excites
  15. L10:2399 weakly excites
  16. L0:2820 weakly excites
  17. L9:2467 weakly excites
  18. L7:2435 weakly suppresses
  19. L2:2992 weakly excites
  20. L10:64 weakly suppresses
  21. L6:2368 weakly suppresses
  22. L4:1312 weakly suppresses
  23. L10:2076 weakly excites
  24. L4:3025 weakly suppresses

Feeds later layers

  1. L13:1981 excites
  2. L18:2284 suppresses
  3. L13:2961 suppresses
  4. L17:539 excites
  5. L16:1678 suppresses
  6. L18:2643 suppresses
  7. L24:954 weakly suppresses
  8. L12:1744 weakly excites
  9. L13:3051 weakly excites
  10. L26:1958 weakly suppresses
  11. L16:2997 weakly excites
  12. L16:2314 weakly suppresses
  13. L17:1916 weakly excites
  14. L12:839 weakly excites
  15. L19:1219 weakly excites
  16. L18:2027 weakly suppresses
  17. L14:605 weakly excites
  18. L22:1555 weakly suppresses
  19. L23:1908 weakly excites
  20. L22:2213 weakly excites
  21. L21:1642 weakly excites
  22. L16:2871 weakly suppresses
  23. L17:2673 weakly suppresses
  24. L14:2623 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.

2 values between -0.99 and -0.941 values between -0.77 and -0.711 values between -0.71 and -0.662 values between -0.66 and -0.602 values between -0.60 and -0.555 values between -0.55 and -0.4919 values between -0.49 and -0.4323 values between -0.43 and -0.3854 values between -0.38 and -0.32106 values between -0.32 and -0.27169 values between -0.27 and -0.21293 values between -0.21 and -0.15447 values between -0.15 and -0.10583 values between -0.10 and -0.04702 values between -0.04 and 0.01598 values between 0.01 and 0.07400 values between 0.07 and 0.13257 values between 0.13 and 0.18125 values between 0.18 and 0.2469 values between 0.24 and 0.2922 values between 0.29 and 0.3518 values between 0.35 and 0.416 values between 0.41 and 0.462 values between 0.46 and 0.521 values between 0.85 and 0.911 values between 1.19 and 1.25offnegativepositiveoften

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. 蔚
  2. dez
  3. iska
  4. Förder
  5. ensem
  6. icone
  7. mieux
  8. heit
  9. skies
  10. BEST

Suppresses

  1. changes
  2. 变化
  3. 那次
  4. 的变化
  5. ModifiedDate
  6. 修改
  7. 갱
  8. 直接影响
  9. 改变
  10. changed