© 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. 4979
    Prev
    Next
    INDEX
    Explanations

    method or methods

    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
    ocking
    -0.10
    otime
    -0.10
    ajs
    -0.10
    ä¸įåģļ
    -0.09
    çļĦä½įç½®
    -0.09
    LICENSE
    -0.09
     ÑĢоли
    -0.09
    æ³±
    -0.08
    åĨĴåĩº
    -0.08
    azon
    -0.08
    POSITIVE LOGITS
    (Method
    0.13
    .getMethod
    0.11
    ras
    0.11
    æīĭ段
    0.11
     æĸ¹æ³ķ
    0.10
    è¿Ļç§įæĸ¹æ³ķ
    0.10
    METHOD
    0.09
    .method
    0.09
    论
    0.09
    WebRequest
    0.09
    Activations Density 0.191%

    No Known Activations