© 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. 1647
    Prev
    Next
    INDEX
    Explanations

    names followed by initials or suffixes

    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
    ç´§
    -0.12
    (CancellationToken
    -0.09
    紧紧
    -0.09
    è¦ģç´§
    -0.08
    comb
    -0.08
     Manning
    -0.08
    ç·Ĭ
    -0.08
    çIJĨæĥ³çļĦ
    -0.08
    æĨ¨
    -0.08
    çIJĨæĥ³
    -0.08
    POSITIVE LOGITS
    urge
    0.10
    elligence
    0.10
    æĭĤ
    0.09
    温æĥħ
    0.09
    ê¹Į
    0.08
    æ¯ķç«Łæĺ¯
    0.08
    [,]
    0.08
    ehler
    0.08
    ultz
    0.08
    hift
    0.08
    Activations Density 0.286%

    No Known Activations