© 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. 5954
    Prev
    Next
    INDEX
    Explanations

    Esperanto, Jewish terms, Zisk

    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
    å¥ĭæĸĹ缮æłĩ
    -0.09
    è¦ģ说
    -0.09
    æ¯ı个人çļĦ
    -0.08
    åĿIJçĿĢ
    -0.08
    宣è¨Ģ
    -0.07
     ÑĢазвива
    -0.07
    为主ä½ĵ
    -0.07
     Keith
    -0.07
    NA
    -0.07
     Cros
    -0.07
    POSITIVE LOGITS
    ilt
    0.09
    ikel
    0.09
    éªł
    0.09
    åĴª
    0.09
    æĭĺ
    0.09
    zer
    0.09
    Trump
    0.08
    бл
    0.08
    褡
    0.08
    witch
    0.08
    Activations Density 0.008%

    No Known Activations