© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12151
    Prev
    Next
    INDEX
    Explanations

    interactive maps and street view

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¤įåį°
    -0.10
    åıij表äºĨ
    -0.09
    书ç±į
    -0.09
    æĻĵå¾Ĺ
    -0.09
    æĹłæĥħ
    -0.09
    ино
    -0.09
    æĬ¥è®°èĢħ
    -0.09
    DMIN
    -0.09
    åħĪ导
    -0.09
    seo
    -0.09
    POSITIVE LOGITS
    èĻļæĭŁ
    0.12
     interactive
    0.11
    interactive
    0.10
    交äºĴ
    0.10
     virtual
    0.10
    ä¸īç»´
    0.10
    åľ¨çº¿
    0.09
     Interactive
    0.09
    é«ĺæ¸ħ
    0.09
    åįļçī©
    0.09
    Activations Density 0.058%

    No Known Activations