© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9751
    Prev
    Next
    INDEX
    Explanations

    so many, so simple, so blind, so much

    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
    ä¸Ģå®ļ
    -0.09
    ç¾½æ¯Ľ
    -0.09
    unity
    -0.09
    ä¸Ģå®ļç¨ĭ度
    -0.08
    okus
    -0.08
    Fld
    -0.08
    è¿ĻæŶåĢĻ
    -0.08
    å¦Ĥå®ŀ
    -0.08
    æľīæīĢ
    -0.08
    ÙĨÙĬÙĨ
    -0.08
    POSITIVE LOGITS
    endet
    0.09
    adem
    0.09
    è·¨çķĮ
    0.09
    endi
    0.09
     Vander
    0.09
    ç°¿
    0.09
    меÑģ
    0.08
    åij¨å¹´
    0.08
    ç»ıåħ¸çļĦ
    0.08
    lord
    0.08
    Activations Density 0.039%

    No Known Activations