© 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. 27843
    Prev
    Next
    INDEX
    Explanations

    Bale, Foles, Wiggins, Blunt

    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
    çłĶ究ä¸Ńå¿ĥ
    -0.11
    èĢģ人家
    -0.10
    elen
    -0.10
    è¿ĻæĶ¯
    -0.09
    ä¾µçĬ¯
    -0.09
    çİĭçĪ·
    -0.09
    为ä¸Ńå¿ĥ
    -0.09
    Translation
    -0.09
    æĥłå·ŀ
    -0.09
    æĶ¶åĽŀ
    -0.09
    POSITIVE LOGITS
    åīį身
    0.10
    èĦ±é¢ĸèĢĮåĩº
    0.10
    æĪIJéķ¿
    0.09
    åĢį
    0.09
    èį¡
    0.09
    代
    0.08
    ÑĢаÐ
    0.08
    SAT
    0.08
    æİĴè¡Į
    0.08
    FY
    0.08
    Activations Density 0.266%

    No Known Activations