© 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. 50235
    Prev
    Next
    INDEX
    Explanations

    healthcare related terms and care

    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
    åħ±æĮ¯
    -0.09
    è¿ĻåĿĹ
    -0.09
    ä¸įåŃķ
    -0.09
    诩
    -0.08
    åģļ强
    -0.08
    人æµģ
    -0.08
    èł¢
    -0.08
     blister
    -0.08
    (fig
    -0.08
    idd
    -0.08
    POSITIVE LOGITS
     Redistributions
    0.09
    家å±ŀ
    0.09
    åĮ»æĬ¤
    0.09
    à¸ķรา
    0.08
    éĢĤå®ľ
    0.08
    確實
    0.08
    оде
    0.08
    ournée
    0.08
    åij¼åı«
    0.08
    uzzi
    0.08
    Activations Density 0.230%

    No Known Activations