© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51708
    Prev
    Next
    INDEX
    Explanations

    Pablo Picasso, Bertrand Russell, John F. Kennedy

    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
    诸å¦Ĥ
    -0.10
    s
    -0.09
    åĬªåĬĽ
    -0.09
    çŃīæĸ¹éĿ¢çļĦ
    -0.08
    hil
    -0.08
    studio
    -0.08
     aud
    -0.08
    å¯Ĵåģĩ
    -0.08
    è¾Ľåĭ¤
    -0.08
    ᶣ
    -0.08
    POSITIVE LOGITS
    éļ¾æĢª
    0.10
    è¿Ļåı¥è¯Ŀ
    0.10
    æĹ¥æĬ¥è®°èĢħ
    0.09
    /on
    0.09
    reamble
    0.09
    ElementException
    0.09
    ä¸įæŃ¢
    0.09
    казÑĭваеÑĤ
    0.08
    former
    0.08
     safeg
    0.08
    Activations Density 0.093%

    No Known Activations