© 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. 35494
    Prev
    Next
    INDEX
    Explanations

    catheter insertion and related procedures

    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
    tm
    -0.09
    æľīéĴĪ对æĢ§
    -0.09
    ä¸ĢçĶŁ
    -0.08
    æĪIJåĪĨ
    -0.08
    brid
    -0.08
    æĪIJ份
    -0.08
    ä¸įå¼Ģ
    -0.08
     Mour
    -0.08
    yz
    -0.08
    åİ»çľĭ
    -0.08
    POSITIVE LOGITS
    cesso
    0.09
    说çļĦè¯Ŀ
    0.09
    .communic
    0.09
    åħ¨
    0.09
    è¿ĩå¹´
    0.09
    MPI
    0.09
    _MARKER
    0.09
    寸
    0.09
    åģļçļĦäºĭæĥħ
    0.09
    æľĽ
    0.09
    Activations Density 0.261%

    No Known Activations