© 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. 31215
    Prev
    Next
    INDEX
    Explanations

    whatever

    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
    æ¯ıä¸Ģ个
    -0.11
    æ¯ı个人éĥ½
    -0.10
    enor
    -0.09
    æľīå¾Īå¤ļ
    -0.09
    åı¯ä¸įæĺ¯
    -0.08
     Cord
    -0.08
    axed
    -0.08
    ä¸ĩ象
    -0.08
    бо
    -0.08
    æ¯ıä¸Ģ个人
    -0.08
    POSITIVE LOGITS
    æĢ»ä¹ĭ
    0.10
     whichever
    0.10
    .Persistence
    0.09
    å½ĵåľ°çļĦ
    0.09
    æĤ¨çļĦåŃ©åŃIJ
    0.09
    ä¸į论
    0.09
    æ¾¹
    0.09
     contr
    0.09
     whatever
    0.09
    ELSE
    0.09
    Activations Density 0.037%

    No Known Activations