© 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. 57206
    Prev
    Next
    INDEX
    Explanations

    three new

    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
    çļĦåIJĦç§į
    -0.11
    çļĦåIJĦ项
    -0.11
     ones
    -0.09
    天天
    -0.09
    èĥĮä¸Ĭ
    -0.09
    ses
    -0.09
    /trunk
    -0.09
     Gaut
    -0.08
    _TERMIN
    -0.08
    ç§įç§į
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.12
    éĩįè¦ģçļĦ
    0.11
    éĩįçĤ¹å·¥ä½ľ
    0.11
    æĸ°çļĦ
    0.10
    åħ¨æĸ°çļĦ
    0.10
    /all
    0.10
    å¾Īéĩįè¦ģçļĦ
    0.10
    æĸ¹éĿ¢çļĦ
    0.09
    åĵģçīĮçļĦ
    0.09
    éĿŀ常好çļĦ
    0.09
    Activations Density 0.183%

    No Known Activations