© 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. 59097
    Prev
    Next
    INDEX
    Explanations

    get ... whatever

    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
    åħ¸
    -0.09
    axes
    -0.09
    IJ
    -0.09
    ä¸Ńå¿ĥåŁİå¸Ĥ
    -0.09
    SPACE
    -0.09
     Durant
    -0.08
    ä»İæĿ¥
    -0.08
    олоÑģ
    -0.08
    ä½łçŁ¥éģĵ
    -0.08
    æİ¥ä¸ĭæĿ¥
    -0.08
    POSITIVE LOGITS
    æļ´éĽ¨
    0.09
    ä¸Ģé¦ĸ
    0.08
    åīįæīĢ
    0.08
    åıĭåĸĦ
    0.08
    è¿ŀéĶģ
    0.08
    ä¸įä¸Ģæł·çļĦ
    0.08
    ä¸įåĪ°
    0.08
     yaklaÅŁ
    0.08
    marsh
    0.08
    HD
    0.08
    Activations Density 0.091%

    No Known Activations