© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 926
    Prev
    Next
    INDEX
    Explanations

    parts of biological entities

    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
    åľ¨éĩĮéĿ¢
    -0.12
     اÙĦعرا
    -0.11
    ĵåIJį
    -0.10
    OMEM
    -0.10
    ç²¾é«ĵ
    -0.10
    ŀæĢ§
    -0.09
    âĸ£
    -0.09
    è¿Ļä¹Łæĺ¯
    -0.09
    alendar
    -0.09
    è¿ĻäºĽéĥ½æĺ¯
    -0.09
    POSITIVE LOGITS
     “
    0.07
    为å¥ijæľº
    0.07
     (...)
    0.07
    为æĬĵæīĭ
    0.07
    æī§åĭ¤
    0.06
    åIJĮåŁİ
    0.06
     (~
    0.06
    为ä¾ĭ
    0.06
    å®ļçĤ¹
    0.05
    “
    0.05
    Activations Density 11.244%

    No Known Activations