© 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. 22525
    Prev
    Next
    INDEX
    Explanations

    collection of vintage and historic items

    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
    殿
    -0.10
    æĸ°æµªå¾®åįļ
    -0.10
    éĵ¶æ²³
    -0.09
    ç»ĻåŃ©åŃIJ
    -0.09
    åħ¨äº§ä¸ļéĵ¾
    -0.08
    bid
    -0.08
    ä¸Ģ声
    -0.08
    åĸ§
    -0.08
    欢è¿İæĤ¨
    -0.08
    æĵįåľº
    -0.08
    POSITIVE LOGITS
    arda
    0.12
    书ç±į
    0.09
     обо
    0.09
    大大å°ı
    0.09
    faction
    0.09
    ÑĩиÑģлен
    0.08
    uco
    0.08
    åĽ½åĨħå¤ĸ
    0.08
    æł¹åºķ
    0.08
    åIJĦå¼ı
    0.08
    Activations Density 0.034%

    No Known Activations