© 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. 34875
    Prev
    Next
    INDEX
    Explanations

    events occurred

    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
    è¿Ļå¼ł
    -0.10
    çłĢ
    -0.10
    ç»Ļ人
    -0.09
     Pars
    -0.09
    ÑĢеÑģÑĤ
    -0.09
    ä¸Ģå¼ł
    -0.09
    lix
    -0.08
    ä»ĸä»¬åľ¨
    -0.08
    ãģĦãģ¾ãģĻ
    -0.08
    åıĪ称
    -0.08
    POSITIVE LOGITS
    äººæł¼
    0.10
     ЮÑĢ
    0.09
    åºŃ
    0.09
    /is
    0.09
    åģİ
    0.09
    æłijæŀĿ
    0.09
    è¾ķ
    0.08
    ément
    0.08
    åĴ»
    0.08
     nonetheless
    0.08
    Activations Density 0.037%

    No Known Activations