© 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. 47713
    Prev
    Next
    INDEX
    Explanations

    in favor of

    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
     ë¬¼ë¡ł
    -0.11
    çī¢
    -0.10
    以为
    -0.09
    /moment
    -0.09
    .localized
    -0.09
    ILA
    -0.09
    éĹ»è¨Ģ
    -0.08
    ÑĮÑİ
    -0.08
    ä¸ĭ称
    -0.08
    orning
    -0.08
    POSITIVE LOGITS
     него
    0.11
    çļĦ姿æĢģ
    0.09
    /on
    0.09
    èĦIJ
    0.09
    åħĭæĸ¯
    0.09
    建设åĴĮ
    0.09
    æĭ¢
    0.08
    mand
    0.08
    Caller
    0.08
    ASTER
    0.08
    Activations Density 0.005%

    No Known Activations