© 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. 33777
    Prev
    Next
    INDEX
    Explanations

    additional works at

    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
    erton
    -0.08
    GR
    -0.08
    尤为
    -0.08
    æĢ¯
    -0.08
    æĢĽ
    -0.08
    дÑĥ
    -0.08
    è¸ı
    -0.07
    ÑģÑĥ
    -0.07
    EndPoint
    -0.07
    æīĢå¾Ĺ
    -0.07
    POSITIVE LOGITS
    ä¸įéĹ´æĸŃ
    0.10
    æĽ´å¤ļ精彩
    0.10
    æ¯ı天éĥ½
    0.09
    æ¯ıæĹ¥
    0.09
    ä¸įå®ļ
    0.09
    å¤ļå¤ļ
    0.09
    argas
    0.09
    ULD
    0.08
    uide
    0.08
    æĭĪ
    0.08
    Activations Density 0.021%

    No Known Activations