© 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. 39983
    Prev
    Next
    INDEX
    Explanations

    compliance with regulations

    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
    eten
    -0.10
    èĤ´
    -0.09
    ral
    -0.09
    ãĤĦãģ¯ãĤĬ
    -0.09
    ling
    -0.09
    eller
    -0.09
    åĿĽ
    -0.09
    éħĿ
    -0.08
    mand
    -0.08
    /vendors
    -0.08
    POSITIVE LOGITS
     minded
    0.11
    -minded
    0.10
    åĴĮæĬĢæľ¯
    0.10
    æĢ§çļĦ
    0.09
    æĢ§
    0.09
    ìĦ¼íĦ°
    0.09
    ueur
    0.09
     Angelo
    0.09
    泪水
    0.09
    prob
    0.08
    Activations Density 0.020%

    No Known Activations