© 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. 35332
    Prev
    Next
    INDEX
    Explanations

    now followed by current status

    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
    ä¸ĩä¸Ģ
    -0.09
    ä¸įå¾Ĺä¸į
    -0.08
     forthcoming
    -0.08
    åĪļæīį
    -0.08
    è´¨åľ°
    -0.08
    äºĽ
    -0.08
     Fac
    -0.08
    atal
    -0.08
    æĢİ
    -0.08
    .fac
    -0.08
    POSITIVE LOGITS
     Garner
    0.10
    adays
    0.09
    urga
    0.09
    åłĻ
    0.09
    æľī两ç§į
    0.09
    æıIJä¾ĽæĽ´å¤ļ
    0.09
    èĽĻ
    0.08
     гоÑĤов
    0.08
    oug
    0.08
    æ¯Ĥ
    0.08
    Activations Density 0.034%

    No Known Activations