© 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. 2653
    Prev
    Next
    INDEX
    Explanations

    licenses and permissions

    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
    绿
    -0.09
    è¾Ł
    -0.08
    vice
    -0.08
    cam
    -0.08
    åIJİæľŁ
    -0.08
     dipped
    -0.08
    elong
    -0.08
    ino
    -0.08
    alysis
    -0.07
    AGES
    -0.07
    POSITIVE LOGITS
    åķĨä¸ļåĮĸ
    0.10
    æ¿Ĵ
    0.10
    à¸ķรา
    0.09
    æijĬ
    0.09
    å°¼äºļ
    0.09
    èĥĮçĿĢ
    0.09
    apor
    0.09
    ç½ijç»ľä¼łæĴŃ
    0.09
    é¡¿
    0.09
    çŃ¹èµĦ
    0.09
    Activations Density 0.155%

    No Known Activations