© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7117
    Prev
    Next
    INDEX
    Explanations

    talking about rankings and search

    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¸įçĶ¨æĭħå¿ĥ
    -0.10
    ä»ĸ们ä¼ļ
    -0.10
    æįı
    -0.09
    eton
    -0.09
    æĴ®
    -0.09
    广åijĬæľįåĬ¡
    -0.09
    åķ®
    -0.09
    ä»ĸ们éĥ½
    -0.09
    æĬĢæľ¯æĶ¯æĮģ
    -0.09
    _pct
    -0.08
    POSITIVE LOGITS
    ç«ŀ
    0.09
    æݨå¼Ģ
    0.09
    æŁIJä¸Ģ
    0.08
    åİĺ
    0.08
    ORIES
    0.08
    亲
    0.08
    âĶ´
    0.08
    zers
    0.08
    .positions
    0.08
    åįĥåħĥ
    0.08
    Activations Density 0.034%

    No Known Activations