© 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. 978
    Prev
    Next
    INDEX
    Explanations

    Non-Argument Calendar

    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
    ä¸įå¦Ĥ
    -0.11
    没éĶĻ
    -0.11
    èĢĮä¸įæĺ¯
    -0.10
    ä¸įæĢķ
    -0.10
    ä¸įä¸ĭ
    -0.10
    ä¸įå¤Ł
    -0.10
    è¿ĺæĺ¯
    -0.10
    ä¸įä¸Ģæł·çļĦ
    -0.10
     intern
    -0.09
    ä¸į容æĺĵ
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.14
     anymore
    0.11
    èĢĮæĺ¯
    0.11
    etheless
    0.11
    theless
    0.10
     necessarily
    0.10
    ä¸ĵä¸ļ人士
    0.10
    chal
    0.10
    ä¹Łä¸įæĥ³
    0.10
     há»ģ
    0.10
    Activations Density 0.126%

    No Known Activations