© 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. 2782
    Prev
    Next
    INDEX
    Explanations

    2-in-1

    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¿·æĥij
    -0.08
    ä¸įä¸ĭ
    -0.08
    æĶ¯éħį
    -0.08
    æł¸å®ļ
    -0.08
    奴
    -0.08
    æ¾Ī
    -0.08
    è¿·
    -0.08
    åī½
    -0.08
    emies
    -0.08
    ilters
    -0.08
    POSITIVE LOGITS
    ä¸Ģ对ä¸Ģ
    0.11
    ä¸Ģç«Ļ
    0.10
    .gg
    0.10
    åIJĪä¸Ģ
    0.09
    fromJson
    0.09
    æĽĻ
    0.09
    ä¸įå°½
    0.08
    æľīçĶ¨
    0.08
    çļĦæľºä¼ļ
    0.08
    :variables
    0.08
    Activations Density 0.069%

    No Known Activations