© 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. 55733
    Prev
    Next
    INDEX
    Explanations

    essays for dating forum

    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
    çıįçıł
    -0.09
    IEW
    -0.08
    okie
    -0.08
     Miner
    -0.08
    ä¸įåĩĨ
    -0.08
    ihar
    -0.08
    ious
    -0.08
    ãģĦãģ£ãģŁ
    -0.07
    loff
    -0.07
     Wolff
    -0.07
    POSITIVE LOGITS
    ä¸ĢåIJį
    0.10
    mtree
    0.10
    ä¸Ģä½į
    0.09
    澧
    0.09
    æĽ¿
    0.09
    ali
    0.09
    è´µ
    0.08
    ä¸Ģç»ı
    0.08
    èĪį
    0.08
    大äºĭ
    0.08
    Activations Density 0.270%

    No Known Activations