© 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. 35424
    Prev
    Next
    INDEX
    Explanations

    such activities or efforts

    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
    è¿Ļæł·çļĦ
    -0.11
    è¿Ļç§įæĥħåĨµ
    -0.10
    ä¸ĢæĿ¡é¾Ļ
    -0.09
    éĢĻ樣çļĦ
    -0.09
    éĢĻ種
    -0.09
    иÑĪÑĮ
    -0.09
    奥æŀĹåĮ¹
    -0.09
    ä¸ĢéĿ¢
    -0.09
     bare
    -0.08
    ussen
    -0.08
    POSITIVE LOGITS
    ãģij
    0.09
    ç»ıå¼Ģ
    0.09
    веÑĤ
    0.08
    fact
    0.08
    æ®Ĵ
    0.08
    iner
    0.08
    ropa
    0.08
    夹
    0.07
    urgeon
    0.07
    çĹ
    0.07
    Activations Density 0.343%

    No Known Activations