© 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. 31966
    Prev
    Next
    INDEX
    Explanations

    first derivative

    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
    éĤ¯
    -0.09
    ä¸ĢçĽ´åľ¨
    -0.08
    asure
    -0.08
    æĺİç¡®è§Ħå®ļ
    -0.08
    inth
    -0.08
    ç²¥
    -0.08
    æľĿ
    -0.08
     Zucker
    -0.08
    ä»ĸæĺ¯
    -0.08
     tapi
    -0.08
    POSITIVE LOGITS
    ê·Ģ
    0.09
    éŀł
    0.09
    æ»¨æ±Ł
    0.09
    å²ģ
    0.09
    ä¸Ńæĸ°
    0.09
    ksz
    0.09
    æĹłå£°
    0.09
    ãĥįãĤ¿
    0.09
    注æĺİæĿ¥æºIJ
    0.08
    沿
    0.08
    Activations Density 0.002%

    No Known Activations