© 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. 48688
    Prev
    Next
    INDEX
    Explanations

    quarterback positions

    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
    emean
    -0.10
    quares
    -0.09
    æŁIJç§įç¨ĭ度
    -0.09
    uration
    -0.09
    å¯Įè£ķ
    -0.09
    fte
    -0.09
    CHANT
    -0.08
     chocolates
    -0.08
    ANGLE
    -0.08
    ris
    -0.08
    POSITIVE LOGITS
    å¨ĺ
    0.11
    innen
    0.10
    æ»Ĥ
    0.09
    emu
    0.09
    й
    0.09
    人éĢī
    0.08
    iler
    0.08
    æºŁ
    0.08
    æĺı
    0.08
    çªĿ
    0.08
    Activations Density 0.004%

    No Known Activations