© 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. 53565
    Prev
    Next
    INDEX
    Explanations

    pediatric, pedagogy, pediatrics, pedagogue

    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
     оказÑĭва
    -0.10
    æľ¬ç½ijç«Ļ
    -0.09
    pat
    -0.08
    ATS
    -0.08
    yx
    -0.08
    gn
    -0.08
    วà¸Ķ
    -0.08
    ingly
    -0.08
    cy
    -0.08
    mask
    -0.08
    POSITIVE LOGITS
    æĻķ
    0.10
    oux
    0.09
    æīĭæ³ķ
    0.09
    ueling
    0.09
    åįģ足
    0.09
    éªŀ
    0.09
    éªĸ
    0.09
    åľ¨è·¯ä¸Ĭ
    0.09
    acia
    0.09
    峤
    0.09
    Activations Density 0.015%

    No Known Activations