© 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. 17076
    Prev
    Next
    INDEX
    Explanations

    hip arthroplasty

    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¸Ģ级
    -0.09
     беÑĢем
    -0.09
    åĥ®
    -0.09
    .getClassName
    -0.09
    èĭ¥æľī
    -0.09
    æĿı
    -0.09
    导读
    -0.09
    ADDING
    -0.09
    æŃ£éĿ¢
    -0.09
    >Main
    -0.09
    POSITIVE LOGITS
    é»ijé¾Ļ
    0.10
    骨
    0.10
    éĶ»éĢł
    0.09
    éĵºè®¾
    0.09
    razier
    0.09
    æĶ¶èİ·
    0.09
    æĶ¶çĽĬ
    0.08
     hip
    0.08
    å·¥ç¨ĭæľºæ¢°
    0.08
    æ¯Ĥ
    0.08
    Activations Density 0.460%

    No Known Activations