© 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. 34007
    Prev
    Next
    INDEX
    Explanations

    collection

    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
    bpp
    -0.10
     Alley
    -0.09
    åīį沿
    -0.09
    peria
    -0.09
    è¯Ĥ
    -0.09
    é¦Ĵ头
    -0.09
    çłĶ究éĻ¢
    -0.09
    vir
    -0.09
    ä¸Ģè¶Ł
    -0.09
     SimpleName
    -0.09
    POSITIVE LOGITS
    rou
    0.10
    壮大
    0.10
    éĩı
    0.09
    æĪ·
    0.08
     pew
    0.08
    Accessor
    0.08
     tar
    0.08
    ç·Ĭ
    0.08
    .Direction
    0.08
    æĸ¹åIJij
    0.07
    Activations Density 0.046%

    No Known Activations