© 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. 17870
    Prev
    Next
    INDEX
    Explanations

    information about health and science

    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
    _icall
    -0.11
    _OM
    -0.10
    çľĭä½ł
    -0.10
    çķ¶æĤ¨åľ¨
    -0.10
    .shadow
    -0.09
    æľīä¸įåIJĮçļĦ
    -0.09
    对该
    -0.09
    FunctionFlags
    -0.09
    æĬĬè¿ĻäºĽ
    -0.09
    èIJ¥éĢł
    -0.09
    POSITIVE LOGITS
    带æĿ¥çļĦ
    0.10
    çļĦæľĢä½³
    0.09
     Lansing
    0.09
    -related
    0.09
    èĨ
    0.09
    æīĢ带æĿ¥çļĦ
    0.08
    AW
    0.08
    -focused
    0.08
    äºŃ
    0.08
    æĸ¹éĿ¢çļĦ
    0.08
    Activations Density 1.062%

    No Known Activations