© 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. 58156
    Prev
    Next
    INDEX
    Explanations

    after ATP

    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
    ç¼Ĩ
    -0.11
    祯
    -0.10
    ãģĽãģĦ
    -0.10
    amate
    -0.09
    mouth
    -0.09
    æĶ¶è´¹
    -0.09
    bru
    -0.09
    ä¸Ģå¹ķ
    -0.09
    gni
    -0.09
     Ferd
    -0.09
    POSITIVE LOGITS
    ä¾
    0.09
    裸
    0.08
    临
    0.08
    è´¯
    0.08
    pper
    0.08
    ç»ıæµİæĬĢæľ¯
    0.08
    èĩ¨
    0.08
    ç½¢
    0.08
    æĮģ
    0.08
    躬
    0.08
    Activations Density 0.002%

    No Known Activations