© 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. 2273
    Prev
    Next
    INDEX
    Explanations

    Adele, Adecco, Adelaide

    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
    表述
    -0.09
    æĹ»
    -0.09
    ä¸įåIJĮæĦı
    -0.08
    è°·
    -0.08
    ç¾İæľ¯
    -0.08
    é½
    -0.08
    è¿Ļåı¥è¯Ŀ
    -0.08
    åı¥è¯Ŀ
    -0.08
    æĮĤçĿĢ
    -0.08
     sac
    -0.08
    POSITIVE LOGITS
    ipop
    0.11
     lắng
    0.09
    åįĬå°ıæŶ
    0.09
    _MPI
    0.09
    åŁ´
    0.09
    calar
    0.09
    æ¸ħåĩĢ
    0.09
    å²ĺ
    0.09
    ucht
    0.08
    ÑģÑĤÑĢа
    0.08
    Activations Density 0.004%

    No Known Activations