© 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. 27330
    Prev
    Next
    INDEX
    Explanations

    local and nearby 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
    çļĦä¸Ģ大
    -0.10
    ç»ıåķĨ
    -0.09
    åĬ¡
    -0.09
    æķ´ä¸ª
    -0.09
    åĭĻ
    -0.09
    ä¹Ĵä¹ĵ
    -0.09
    æ»ļæ»ļ
    -0.08
    icular
    -0.08
    åѦä½į
    -0.08
    ä¸ĢåĪĢ
    -0.08
    POSITIVE LOGITS
    å¶Ļ
    0.08
    æĩ¿
    0.08
    [loc
    0.08
    สà¸ĸา
    0.08
    建档
    0.08
    å±Ģéĥ¨
    0.08
    /local
    0.08
    alsy
    0.08
    æĦı大
    0.08
    Sdk
    0.07
    Activations Density 0.034%

    No Known Activations