© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60938
    Prev
    Next
    INDEX
    Explanations

    vaginal medical terms

    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
    ä¸ŃåĽ½çī¹èī²
    -0.09
    ween
    -0.08
    å¾Īå·®
    -0.08
    aname
    -0.08
    AFP
    -0.08
     Ev
    -0.08
    åıªèĥ½è¯´
    -0.08
    诿
    -0.08
    igin
    -0.08
    ceed
    -0.08
    POSITIVE LOGITS
    æ£ķèī²
    0.10
    åĪĨ娩
    0.09
    sis
    0.09
    ä¸įä¸ĭ
    0.09
    .Var
    0.09
    gles
    0.08
    æ·±å¤Ħ
    0.08
    ukt
    0.08
     Bj
    0.08
    建设åĴĮ
    0.08
    Activations Density 0.014%

    No Known Activations