© 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. 11546
    Prev
    Next
    INDEX
    Explanations

    Buddha, Hitler, Einstein, Aristotle

    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
    ï¸ı
    -0.10
    eeper
    -0.08
    榫
    -0.08
    no
    -0.08
    iers
    -0.08
     ÑĢÑĭ
    -0.08
    kes
    -0.08
     rein
    -0.08
    nyder
    -0.08
    骨头
    -0.08
    POSITIVE LOGITS
    reich
    0.09
    âĢ¾
    0.09
    ium
    0.09
    zeit
    0.09
    ä¹ĭè·¯
    0.09
    ĥģ
    0.09
    ä¿®è¡Į
    0.08
    æĤ¨çļĦ
    0.08
    ubar
    0.08
     Buddha
    0.08
    Activations Density 0.010%

    No Known Activations