© 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. 22839
    Prev
    Next
    INDEX
    Explanations

    Emily Dickinson

    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
    幺
    -0.10
    ibs
    -0.10
    ../../../
    -0.10
    ì§ĵ
    -0.09
    lä
    -0.08
    ä¼į
    -0.08
    æĥ³æĥ³
    -0.08
    人æ°ijæľįåĬ¡
    -0.08
    üz
    -0.08
     finest
    -0.08
    POSITIVE LOGITS
    ently
    0.11
    eenth
    0.10
    ä¿Ĺè¯Ŀ说
    0.09
    ìį¨
    0.09
     addCriterion
    0.09
    sek
    0.09
    webtoken
    0.09
    ãģĦãģ£ãģŁ
    0.09
    å¾Īéķ¿
    0.09
    à¹Ħร
    0.09
    Activations Density 0.050%

    No Known Activations