© 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. 20804
    Prev
    Next
    INDEX
    Explanations

    all orders

    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个èģĮä¸ļ
    -0.09
    istine
    -0.09
    вали
    -0.09
    æĹłå¥Ī
    -0.09
    Tek
    -0.08
    æł¹æľ¬
    -0.08
    iges
    -0.08
    å¾Īå°ı
    -0.08
    GetName
    -0.08
    bury
    -0.08
    POSITIVE LOGITS
    精彩çļĦ
    0.10
    ä¸įçĽ¸ä¿¡
    0.10
    ascar
    0.10
    åºĬä¸Ĭ
    0.09
    广åijĬæľįåĬ¡
    0.09
    ä¸įéĢļ
    0.09
    Ñı
    0.09
    plevel
    0.09
    .Fl
    0.08
    èĢħçļĦ
    0.08
    Activations Density 0.047%

    No Known Activations