Neuron Explorer

Qwen3-0.6B

unclear: 'purpose' and words near it

A neuron in layer 12 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 is hard to pin down. It fires on words like 'secure', 'support' and 'found' in academic and descriptive text, and it goes strongly negative on 'purpose' and the word 'be' right before it. Turning it up or down did not show a clear theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. Think it is wrong? Flag it (opens an email to the maker with the neuron already filled in).

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

    railroad, Sacramento quickly saw its population swell in the second half of the 19th century as blue-collar laborers poured into the city in droves to secure work as machinists, painters, carpenters and boilermakers for

  2. #2 peak

    aries). But they differ more than they do resemble each other, when one looks at the details. Comparing them can give us insight into what the Framers found important in 1781, and what they changed their minds on by

  3. #3 peak

    Discussion Area. You should quote or paraphrase from specific pages in the course text to support your claims about philosophical ideas and concepts, using correct APA citation. Start reviewing and

  4. #4 peak

    urative Language Practice Cards provide an easy way to help students develop a critical reading comprehension skill. Each card consists of a leveled passage that contains a form of figurative language. Questions ask students to choose

  5. #5 peak

    the foreign good since it is not available locally, however, they will reluctantly do so.⏎Based on the general theory of ethnocentrism, consumer ethnocentrism is specific to consumers of a particular country. Ethnocentrism refers to

  6. #6 peak

    on where and how the curvature occurs.⏎Kyphosis (also called kyphoscoliosis) is a deep front-to-back curve typically occurring at

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 working on this task, and I have been working on this task. I have been working on this task. I have been working on this task. I have been working on this task. I have been working on this task

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

    into laboratory kits that are complete, well-organised, and properly targeted for temperature-controlled shipping and storage.⏎First, the purpose of the kit or kits must be firmly defined. This is a critical stage, as imprecision in

  2. #2 peak

    in Houston, Texas.⏎Chartered in 1958 by the Secretary of Defense, DDMS was originally formed with the express purpose of providing much needed DoD support to the U.S. initial manned space flight

  3. #3 peak

    , a nine-year venture that existed between 1817 and 1826, whose purpose was to educate and train non-white Christian missionaries. The book focuses upon the evangelical

  4. #4 peak

    saying Social Security and Medicare are bad? The fact of the matter is these programs (along with welfare) were created to do only one thing, take money away from the people who have it, and give it

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. L8:1890 suppresses
  2. L9:2504 excites
  3. L8:2139 suppresses
  4. L11:2555 weakly suppresses
  5. L9:200 weakly suppresses
  6. L9:1505 weakly excites
  7. L10:2075 weakly excites
  8. L11:2819 weakly suppresses
  9. L8:2827 weakly excites
  10. L7:2710 weakly suppresses
  11. L9:2710 weakly excites
  12. L9:1160 weakly excites
  13. L7:2106 weakly suppresses
  14. L9:2451 weakly excites 'for' giving a reason or cause
  15. L3:2607 weakly excites
  16. L11:1790 weakly suppresses
  17. L9:1000 weakly excites
  18. L11:2620 weakly suppresses
  19. L10:2507 weakly excites
  20. L10:1242 weakly suppresses
  21. L7:2843 weakly suppresses
  22. L4:1490 weakly suppresses
  23. L2:2906 weakly excites
  24. L11:255 weakly excites

Feeds later layers

  1. L14:522 excites
  2. L17:1097 suppresses
  3. L16:2424 suppresses
  4. L18:2659 suppresses
  5. L15:515 suppresses word before 'that', 'to' or 'for' continuation
  6. L17:1670 suppresses
  7. L22:2856 suppresses
  8. L14:1306 excites
  9. L15:1887 suppresses
  10. L18:2469 suppresses
  11. L19:2827 suppresses
  12. L17:2014 excites
  13. L16:1449 suppresses
  14. L19:597 suppresses
  15. L19:1912 suppresses
  16. L15:672 weakly suppresses
  17. L22:2793 weakly suppresses
  18. L27:2279 weakly suppresses
  19. L13:1835 weakly suppresses
  20. L20:1861 weakly suppresses
  21. L19:1110 weakly excites
  22. L15:2174 weakly suppresses
  23. L20:928 weakly excites
  24. L19:2993 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.

1 values between -4.81 and -4.661 values between -4.37 and -4.232 values between -3.94 and -3.801 values between -2.79 and -2.642 values between -2.50 and -2.353 values between -1.92 and -1.782 values between -1.78 and -1.632 values between -1.63 and -1.492 values between -1.49 and -1.344 values between -1.34 and -1.205 values between -1.20 and -1.067 values between -1.06 and -0.919 values between -0.91 and -0.7710 values between -0.77 and -0.6221 values between -0.62 and -0.4848 values between -0.48 and -0.33227 values between -0.33 and -0.19938 values between -0.19 and -0.052097 values between -0.05 and 0.10392 values between 0.10 and 0.2493 values between 0.24 and 0.3925 values between 0.39 and 0.538 values between 0.53 and 0.686 values between 0.68 and 0.822 values between 0.82 and 0.96offnegativepositiveoften

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. delay
  2. erview
  3. ahoma
  4. imes
  5. urrence
  6. ippet
  7. stagger
  8. permalink
  9. langue
  10. krit

Suppresses

  1. purpose
  2. 目的
  3. Purpose
  4. Purpose
  5. purposes
  6. task
  7. 用途
  8. tasks
  9. 目标任务
  10. (tasks