© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31422
    Prev
    Next
    INDEX
    Explanations

    set out to

    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
    ç§ģä¸ĭ
    -0.10
    æ¶īå«Į
    -0.09
    æİ¥èijĹ
    -0.09
    æİ¥ä¸ĭæĿ¥
    -0.09
    æİ¥çĿĢ
    -0.09
    æĻ®éģįåŃĺåľ¨
    -0.09
    nelle
    -0.09
    elle
    -0.09
    çľĭä»ĸ
    -0.09
    澡
    -0.09
    POSITIVE LOGITS
    .kotlin
    0.09
    iller
    0.08
    çļĦ第ä¸Ģ个
    0.08
    anner
    0.08
    UNCH
    0.08
    aminer
    0.08
    MISS
    0.08
    æľ¬èĥ½
    0.08
    asar
    0.08
     дÑĥÑħ
    0.08
    Activations Density 0.005%

    No Known Activations