© 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. 54745
    Prev
    Next
    INDEX
    Explanations

    indie artists and songs

    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
    âĿĴ
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
     ÙħØŃÙħ
    -0.09
     ÑģовÑģем
    -0.09
    éĩįå¤į
    -0.09
    éķ¿æľŁ
    -0.09
    è¾ĥå¤ļ
    -0.09
    ãĤĤå¤ļãģĦ
    -0.09
    (Cs
    -0.09
    _CONSOLE
    -0.09
    POSITIVE LOGITS
    ä¸įåIJĮç¨ĭ度
    0.11
    åIJĦè¡ĮåIJĦä¸ļ
    0.11
    æľīä¸įåIJĮçļĦ
    0.10
    ä¸įåIJĮçļĦ
    0.10
    çļĦåIJĦç§į
    0.10
    ä¸Ģ个个
    0.09
    ITE
    0.09
    ä¸įåIJĮç±»åŀĭ
    0.09
     different
    0.09
    åIJĦå¼Ĥ
    0.09
    Activations Density 0.389%

    No Known Activations