© 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. 49601
    Prev
    Next
    INDEX
    Explanations

    total, minimum, maximum, mean, population

    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
    æĹĭ
    -0.11
    ä½łåĸľæ¬¢
    -0.10
    èĵ¬åĭĥ
    -0.10
    antic
    -0.10
    ä¿Ŀ驾
    -0.10
    ä¸īå±Ĥ
    -0.10
    äºĶåħŃ
    -0.09
    åĽĽç§į
    -0.09
    inis
    -0.09
    ä¸īç§į
    -0.09
    POSITIVE LOGITS
    æĢ»
    0.10
     total
    0.09
    diet
    0.09
    總
    0.09
    Serial
    0.09
    ìĭľ
    0.08
    uti
    0.08
    zych
    0.08
    ç«¥
    0.08
    коп
    0.08
    Activations Density 0.134%

    No Known Activations