© 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. 31379
    Prev
    Next
    INDEX
    Explanations

    character encoding

    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
    ä¹Ŀå¹´
    -0.10
    建åĨĽ
    -0.10
    styleType
    -0.09
    ä¸įå¦Ĥ
    -0.09
    æł¼å¼ı
    -0.09
    æĸ½
    -0.09
    OURS
    -0.08
    .Ui
    -0.08
    ookie
    -0.08
    æ¥Ķ
    -0.08
    POSITIVE LOGITS
     Unicode
    0.10
    åħ¨å¥Ĺ
    0.10
    íĭ±
    0.09
    èĦı
    0.09
    ç»Ī究
    0.09
    ISO
    0.09
    Unicode
    0.09
     ISO
    0.09
    äºĮ级
    0.08
    .Unicode
    0.08
    Activations Density 0.240%

    No Known Activations