© 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. 23944
    Prev
    Next
    INDEX
    Explanations

    car brands and organizations

    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
    ibal
    -0.10
    æĸ°äº¬æĬ¥
    -0.10
    BaseContext
    -0.10
    ìĬ¬
    -0.09
    信念
    -0.09
    astes
    -0.09
    è¿Ŀæ³ķçĬ¯ç½ª
    -0.09
    æĹ¶ä»£ä¸ŃåĽ½
    -0.09
    ä¸įå¤ļ
    -0.09
    .handleError
    -0.09
    POSITIVE LOGITS
     Finder
    0.10
    åĴĮæĬĢæľ¯
    0.10
     finder
    0.09
    ä¼Ĺ
    0.09
     Software
    0.08
    ner
    0.08
    计ç®Ĺæľº
    0.08
    finder
    0.08
    åijĬ
    0.08
     jot
    0.08
    Activations Density 1.117%

    No Known Activations