© 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. 17997
    Prev
    Next
    INDEX
    Explanations

    biliary endoprostheses

    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
    è¿ŀè½½
    -0.09
    èĵĿ天
    -0.09
    åĨ·åĨ»
    -0.08
    å½ĴæĿ¥
    -0.08
    ubi
    -0.08
    åĨ»
    -0.08
    æĿ¥åĽŀ
    -0.08
    ãĥ©ãĥ³ãĥī
    -0.08
    æĮĽ
    -0.08
    æĮª
    -0.08
    POSITIVE LOGITS
     Evel
    0.10
    æ¶ī
    0.09
    yth
    0.09
    chos
    0.09
    çĵ¦
    0.09
    å¼Ģåı£
    0.09
    ivil
    0.08
     Stones
    0.08
    èĢĦ
    0.08
    æ·±æ·±åľ°
    0.08
    Activations Density 0.245%

    No Known Activations