© 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. 1682
    Prev
    Next
    INDEX
    Explanations

    new executive positions

    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
    uit
    -0.09
    顽强
    -0.09
    é»ĺå¥ij
    -0.08
    è²Ĥ
    -0.08
    ottage
    -0.08
    è´
    -0.08
    误ä¼ļ
    -0.08
    ÙħÙĬر
    -0.08
    æ´¾
    -0.08
    hoa
    -0.08
    POSITIVE LOGITS
    æĸ°çļĦ
    0.18
    ä¸Ģ个æĸ°çļĦ
    0.13
    æĸ°ãģĹãģĦ
    0.13
    æĸ°ãģŁãģª
    0.12
     new
    0.11
    æĸ°ãģŁ
    0.11
     ìĥĪë¡ľìļ´
    0.11
    ä¸ĭä¸Ģ
    0.10
    æĸ°çļĦä¸Ģ
    0.10
     новÑĭÑħ
    0.10
    Activations Density 0.078%

    No Known Activations