© 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. 3378
    Prev
    Next
    INDEX
    Explanations

    roles and functions

    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
     NK
    -0.08
    åĬª
    -0.08
    让å®ĥ
    -0.08
    æĮŀ
    -0.08
    âĪ
    -0.08
    ä¸Ģç»ı
    -0.08
    æ³®
    -0.07
    åĨĽå·¥
    -0.07
    incy
    -0.07
    表çİ°
    -0.07
    POSITIVE LOGITS
    ä¸ĢéŨ
    0.11
    è¿Ļ个èģĮä¸ļ
    0.10
    èģĮè´£
    0.10
    èĤ©è´Ł
    0.09
    综åIJĪæĢ§
    0.09
    æĹłæīĢ
    0.09
    asl
    0.09
    æī®æ¼Ķ
    0.09
    ä»ĸçŁ¥éģĵ
    0.09
    ä»ĸ们æĺ¯
    0.09
    Activations Density 0.180%

    No Known Activations