© 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. 48118
    Prev
    Next
    INDEX
    Explanations

    sports abbreviations and acronyms

    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
    IDL
    -0.09
    .Handler
    -0.08
    æĸĿ
    -0.08
    /full
    -0.08
    MED
    -0.08
    æĽ©
    -0.08
    åħŃåIJĪ
    -0.08
    èµŁ
    -0.08
    ë°ı
    -0.08
    Nonnull
    -0.08
    POSITIVE LOGITS
    æij¸
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    çĿĢä»ĸ
    0.09
    upid
    0.08
    ively
    0.08
    æĺ¯ä¸Ģ件
    0.08
    gui
    0.08
    ODULE
    0.08
    ({},
    0.08
    åѦä¼ļ
    0.08
    Activations Density 0.200%

    No Known Activations