© 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. 33600
    Prev
    Next
    INDEX
    Explanations

    traffic

    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
    壮
    -0.10
     конÑĤакÑĤ
    -0.09
    builtin
    -0.09
    èĩªä¸»åĵģçīĮ
    -0.09
    èµ°å¾Ĺ
    -0.09
    çIJĨæĥ³çļĦ
    -0.09
     Gast
    -0.09
    壮大
    -0.09
    壯
    -0.09
    éĵ¾æĿ¡
    -0.08
    POSITIVE LOGITS
    æĢİä¹Īçľĭ
    0.09
    æµģéĩı
    0.09
    äºĭåħ³
    0.08
    dock
    0.08
     demon
    0.08
    ç«ĸ
    0.08
    æľīä¿¡å¿ĥ
    0.08
    人æµģ
    0.08
    fen
    0.08
     lantern
    0.08
    Activations Density 0.029%

    No Known Activations