© 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. 58579
    Prev
    Next
    INDEX
    Explanations

    powered by

    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¦ģç´§
    -0.09
    others
    -0.09
    æĿĤçī©
    -0.09
    WithPath
    -0.09
    arts
    -0.09
    åģ¿
    -0.09
     ÑĥнивеÑĢÑģ
    -0.08
     Bis
    -0.08
    常æĢģ
    -0.08
     Newsletter
    -0.08
    POSITIVE LOGITS
    强大
    0.09
    强大çļĦ
    0.09
    powered
    0.09
    象
    0.08
    OPY
    0.08
    -powered
    0.08
    Powered
    0.08
    åIJĮä¸Ģ个
    0.08
    letcher
    0.08
    æľ¬ç«Ļ
    0.08
    Activations Density 0.020%

    No Known Activations