Neuron Explorer

Qwen3-0.6B

unclear: planned or deliberate wording

A neuron in layer 5 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

The top examples are mixed, with a loose thread around words like 'planned', 'deliberate', 'intention' and 'voluntary', plus land plots and lots. It is hard to say what the neuron is really about. Turning it up or down gave text with no clear link to these words.

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

    productive corn field.⏎Two town site promoters, Ace Borger and J.T. Peyton, were engaged. The land was then surveyed, subdivided into blocks, lots, streets, avenues, and alleys. The Stinnett Town site Company

  2. #2 peak

    murdered there, including 960,000 Jews.⏎Auschwitz-Birkenau has become the symbol of the Holocaust and of willful radical evil in our time.⏎What the liberators found in these camps astounded

  3. #3 peak

    of areas as part of our planned SOW.⏎Some key areas are outlined below:⏎At KS3 we cover modules

  4. #4 peak

    the Second World War. By adopting this permissive approach to the right to asylum, the Parliamentary Council (Parlamentarischer Rat) wanted to make a deliberate break with the National Socialist past, which had produced millions of deaths, refugees and

  5. #5 peak

    depicted onto the lot identification plan. Recently, the Land Registry proposes the Land Titles Bill by the replacement of current deeds registration system. However, such proposal has no intention to deal with the long neglected land rights: boundary extent.”⏎Hong Kong represents a

  6. #6 peak

    plan has been in review status for almost 2 years and it appears that DOE's Office of Nuclear Energy has no intention of finalizing the plan.⏎Recommendation: To ensure that an RTG infrastructure

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 be able to do with this, I am. I am. I need to know. I am. I need to know. I need to know. I need to know. I need to know. I need to know

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

    as many base search paths as you like. Here's one that includes⏎/etc as a search path too.<|endoftext|>Salivary gland (Endocrine system)⏎: #1 is , #2 is , #3 is⏎The salivary

  2. #2 peak

    March 10, 2004⏎: The Chilkoot Brown Bear Project⏎I uttered the habitual salutation as I

  3. #3 peak

    second voyage to the New World the French arrived off the coast of Florida on Thursday, June 22, 1564 around three or four o’clock in the afternoon. They landed about thirty leagues south of the St. Johns

  4. #4 peak

    teacher who just lately switched into teaching grade six, I have been on the hunt for middle college teacher sources for the final handful of months. PhD in Unique Education : PhD in Unique Education delivers an write-up about how to assistance students with specific desires

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. L4:896 suppresses
  2. L2:280 excites
  3. L3:75 excites
  4. L0:2137 weakly excites
  5. L1:111 weakly suppresses
  6. L1:1370 weakly suppresses
  7. L2:742 weakly suppresses
  8. L0:574 weakly suppresses
  9. L4:676 weakly suppresses
  10. L0:643 weakly excites
  11. L4:2470 weakly suppresses
  12. L3:2952 weakly excites
  13. L3:2923 weakly suppresses
  14. L3:1903 weakly suppresses
  15. L3:2114 weakly suppresses
  16. L4:2139 weakly suppresses
  17. L2:1910 weakly suppresses
  18. L2:10 weakly suppresses
  19. L3:2656 weakly suppresses
  20. L3:2198 weakly suppresses
  21. L3:248 weakly excites
  22. L4:1881 weakly excites
  23. L4:235 weakly suppresses
  24. L4:330 weakly excites

Feeds later layers

  1. L9:909 suppresses
  2. L20:2537 weakly excites
  3. L6:616 weakly suppresses
  4. L13:210 weakly suppresses
  5. L11:300 weakly suppresses
  6. L22:1163 weakly excites
  7. L16:1662 weakly suppresses
  8. L16:1447 weakly suppresses
  9. L7:26 weakly excites
  10. L27:1498 weakly excites
  11. L22:1118 weakly excites
  12. L10:217 weakly excites
  13. L23:254 weakly suppresses
  14. L10:1866 weakly excites
  15. L17:989 weakly suppresses
  16. L21:2112 weakly excites
  17. L21:2451 weakly excites
  18. L11:2549 weakly suppresses
  19. L19:1063 weakly excites
  20. L10:457 weakly excites
  21. L20:3049 weakly excites
  22. L25:38 weakly suppresses
  23. L22:1352 weakly excites
  24. L19:241 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 -0.84 and -0.802 values between -0.80 and -0.751 values between -0.75 and -0.713 values between -0.66 and -0.622 values between -0.58 and -0.534 values between -0.53 and -0.494 values between -0.49 and -0.445 values between -0.44 and -0.4010 values between -0.40 and -0.3614 values between -0.36 and -0.3126 values between -0.31 and -0.2744 values between -0.27 and -0.2266 values between -0.22 and -0.18118 values between -0.18 and -0.13216 values between -0.13 and -0.09346 values between -0.09 and -0.05788 values between -0.05 and -0.00888 values between -0.00 and 0.04488 values between 0.04 and 0.09342 values between 0.09 and 0.13224 values between 0.13 and 0.18150 values between 0.18 and 0.2278 values between 0.22 and 0.2643 values between 0.26 and 0.3113 values between 0.31 and 0.358 values between 0.35 and 0.407 values between 0.40 and 0.444 values between 0.44 and 0.492 values between 0.49 and 0.533 values between 0.53 and 0.572 values between 0.57 and 0.621 values between 0.62 and 0.661 values between 0.66 and 0.712 values between 0.71 and 0.751 values between 0.80 and 0.841 values between 0.88 and 0.93offnegativepositiveoften

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. 总局
  2. descended
  3. 簠
  4. atat
  5. riff
  6. ;}
  7. GOR
  8. ellers
  9. JsonSerializer
  10. ⟫

Suppresses

  1. ront
  2. .splitext
  3. 凉
  4. ternal
  5. 力还是
  6. ponents
  7. �
  8. ัน
  9. ceptors
  10. �