© 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. 23379
    Prev
    Next
    INDEX
    Explanations

    nutrient absorption and densities

    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
    ×ķת
    -0.12
    OfString
    -0.11
    æŁł
    -0.10
    ett
    -0.09
    dent
    -0.09
    åIJĦç§įåIJĦæł·
    -0.09
    abor
    -0.08
    аÑİÑĤÑģÑı
    -0.08
    ../../../
    -0.08
    屿
    -0.08
    POSITIVE LOGITS
    -rich
    0.10
    rients
    0.09
    è¿ĩåī©
    0.09
    ivot
    0.09
    azar
    0.09
    丰å¯ĮçļĦ
    0.09
    丰å¯Į
    0.09
    lek
    0.09
    FUL
    0.08
    .pivot
    0.08
    Activations Density 0.026%

    No Known Activations