© 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. 18958
    Prev
    Next
    INDEX
    Explanations

    pituitary, adenomas, apoplexy, metastasis

    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
    ä¸įå®Į
    -0.10
    eos
    -0.10
    人大代表
    -0.10
    .annot
    -0.10
    ä¸Ĭ游
    -0.09
    è°İ
    -0.09
    æģŃæķ¬
    -0.09
    å§Ŀ
    -0.09
    RuleContext
    -0.09
    oke
    -0.09
    POSITIVE LOGITS
    æĻķ
    0.09
    ä¸įåĪĨ
    0.09
    å¸Ŀçİĭ
    0.08
    éĴ§
    0.08
     ÑĥÑģл
    0.08
    æŀģ
    0.08
    ç§ijåѦçłĶ究
    0.08
    RESET
    0.08
     disp
    0.08
    ally
    0.08
    Activations Density 0.018%

    No Known Activations