© 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. 53506
    Prev
    Next
    INDEX
    Explanations

    organ transplantation survival

    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
    _TC
    -0.10
    ä¸İæŶ
    -0.09
    สำรวà¸Ī
    -0.09
    BALL
    -0.08
    ursive
    -0.08
    æĢĢåŃķ
    -0.08
    شاء
    -0.08
     Chunk
    -0.08
    ONA
    -0.08
    incare
    -0.08
    POSITIVE LOGITS
    è°ĥæĸĻ
    0.09
    ç«ŀä»·
    0.09
     Greens
    0.09
    çªģå¦Ĥ
    0.09
    æĿµ
    0.09
    allo
    0.09
     Bik
    0.08
    ture
    0.08
    çķ¿
    0.08
     cann
    0.08
    Activations Density 0.674%

    No Known Activations