© 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. 57643
    Prev
    Next
    INDEX
    Explanations

    same or similar

    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
    羣çļĦæĺ¯
    -0.10
    åºı
    -0.10
     дейÑģÑĤвиÑĤелÑĮно
    -0.09
    羣çļĦ
    -0.09
    æ¯ķç«Łæĺ¯
    -0.09
    æĤħ
    -0.09
    æľĢåĸľæ¬¢
    -0.08
    æŀľçĦ¶
    -0.08
    æĻ°
    -0.08
    ews
    -0.08
    POSITIVE LOGITS
    åIJĮæł·çļĦ
    0.12
    ä¸İæѤ
    0.12
    æĥħåĨµ
    0.10
    类似çļĦ
    0.10
    åIJĮæł·
    0.09
    ä¹Łæĺ¯å¦ĤæѤ
    0.09
     situation
    0.09
    æĸ¹å¼ıè¿Ľè¡Į
    0.09
    åIJĮ樣
    0.09
    羸
    0.09
    Activations Density 0.056%

    No Known Activations