© 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. 55439
    Prev
    Next
    INDEX
    Explanations

    institutions after "of"

    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
    eldon
    -0.09
    ä¸ĢåĪĻ
    -0.09
    主宰
    -0.08
     ÐŀÐŀÐŀ
    -0.08
    illed
    -0.08
    leton
    -0.08
    hdl
    -0.08
     bek
    -0.08
    延éķ¿
    -0.07
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.07
    POSITIVE LOGITS
    æĽĻ
    0.10
    èĢģ人家
    0.10
    iset
    0.09
    ä¹Łæ²¡
    0.09
    istik
    0.08
    TZ
    0.08
    ows
    0.08
    åı£ãĤ³ãĥŁ
    0.08
    æŁIJç§į
    0.08
    retty
    0.08
    Activations Density 0.121%

    No Known Activations