© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9493
    Prev
    Next
    INDEX
    Explanations

    file extensions and formats

    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°ĭ
    -0.09
    ä¸ĢæĬĬ
    -0.09
    çļĦè¡Į为
    -0.09
    æĸ°æĺ¥
    -0.09
    ä¸Ģå°ģ
    -0.09
    ç»ıèIJ¥æ´»åĬ¨
    -0.09
    äºĭå®ľ
    -0.09
    就读
    -0.09
    çļĦæł¸å¿ĥ
    -0.08
    astically
    -0.08
    POSITIVE LOGITS
    _tw
    0.09
    éĿĴ
    0.08
     Tristan
    0.08
    lp
    0.08
    大éĻĨ
    0.08
    ware
    0.08
     Phill
    0.07
    çŃīå½¢å¼ı
    0.07
    _lift
    0.07
    propri
    0.07
    Activations Density 0.200%

    No Known Activations