Neuron Explorer

Qwen3-0.6B

mixed, web boilerplate phrases

A neuron in layer 12 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 scattered words in web page clutter, such as 'ago' in 'a year ago', 'by' in 'Posted by', and 'on' in 'first appeared on'. Its strongest negative cases sit right at document breaks and login prompts. Turning it up did not give a clear, consistent theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    of balloons.⏎Submit a review<|endoftext|>1 year ago⏎Verified Sherpa Tutor⏎If a liquid has a definite volume, what

  2. #2 peak

    the all-loving creator who meets every human need. In Psalms we read, “Give thanks to the Lord, for he is good; his love endures forever. Let the redeemed of the Lord tell their story. . . . Let

  3. #3 peak

    ane) and is a natural by-product of gas<|endoftext|>DataTableCollection.Item Property (String)⏎Gets the DataTable object with the specified name.⏎Assembly: System.Data (in System.Data.dll)⏎If a DataTable name exists that matches the case of the search

  4. #4 peak

    world. Proverbs 31:8-9 -- a noble man stands up for what is right and shows concern for others. Such are the sayings of King Lemuel, a noble man belonging to God. Many biblical scholars believe that

  5. #5 peak

    Holman Christian Standard BibleJesus told him, “Foxes have dens, and birds of the sky have nests, but the Son of Man

  6. #6 peak

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

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: The main thing that you have to know, if it's a given. So, you have to be a given, and then be a person, and then be a whole, and then you can't do it without a hat, a

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

    ,0<|endoftext|>Guidelines for Restoring Cultural Landscapes⏎Identifying, retaining and preserving

  2. #2 peak

    , 2012<|endoftext|>Some weather conditions are simply not fun to ride in. As cyclists, windy days

  3. #3 peak

    weaving and entrance ramp studies produced some very significant results, which are discussed in the report and will contribute to overall knowledge of freeway operation.⏎You must be logged in to post a

  4. #4 peak

    liu.<|endoftext|>Bond Price Calculator⏎With this bond price calculator, we aim to help you calculate

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. L9:147 suppresses
  2. L5:414 suppresses
  3. L7:1212 suppresses
  4. L10:169 excites
  5. L11:483 suppresses
  6. L9:1301 excites
  7. L1:2017 suppresses
  8. L3:604 excites
  9. L7:105 excites
  10. L6:1003 excites
  11. L5:1303 weakly excites
  12. L8:24 weakly suppresses
  13. L11:17 weakly suppresses
  14. L4:2500 weakly excites
  15. L9:81 weakly suppresses
  16. L9:253 weakly excites
  17. L4:625 weakly suppresses
  18. L9:1798 weakly suppresses
  19. L4:335 weakly suppresses
  20. L3:323 weakly excites
  21. L6:1576 weakly suppresses
  22. L10:1545 weakly suppresses
  23. L8:254 weakly excites
  24. L4:2289 weakly suppresses

Feeds later layers

  1. L16:248 excites
  2. L14:267 suppresses
  3. L13:283 suppresses
  4. L15:1304 suppresses
  5. L14:1121 suppresses
  6. L18:738 suppresses
  7. L14:84 suppresses
  8. L14:2556 suppresses
  9. L19:446 suppresses
  10. L19:251 suppresses
  11. L17:892 suppresses
  12. L13:2188 suppresses unclear: weak, scattered tokens
  13. L16:275 suppresses
  14. L13:2946 suppresses
  15. L15:1607 suppresses
  16. L19:1273 suppresses
  17. L19:802 excites unclear: word before a company or brand name
  18. L21:105 suppresses
  19. L16:1654 suppresses
  20. L17:841 suppresses
  21. L25:2284 suppresses
  22. L20:151 suppresses
  23. L13:450 excites
  24. L20:573 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 -4.07 and -3.931 values between -3.50 and -3.361 values between -1.07 and -0.922 values between -0.64 and -0.4919 values between -0.49 and -0.35209 values between -0.35 and -0.211134 values between -0.21 and -0.061867 values between -0.06 and 0.08565 values between 0.08 and 0.2296 values between 0.22 and 0.3711 values between 0.37 and 0.511 values between 0.51 and 0.651 values between 1.51 and 1.66offnegativepositiveoften

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. 发生
  2. луш
  3. endency
  4. ăn
  5. ц
  6. ascript
  7. Annotation
  8. annotation
  9. .getContentPane
  10. icon

Suppresses

  1. →del
  2. tür
  3. eil
  4. 五一
  5. functional
  6. terdam
  7. ויות
  8. beit
  9. reno
  10. embar