© 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. 50744
    Prev
    Next
    INDEX
    Explanations

    fellow [group member]

    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
    åıįè¿ĩæĿ¥
    -0.10
    é¢ĺ主
    -0.09
    ãģ»
    -0.09
    elize
    -0.09
    ä»İåݻ年
    -0.08
    _decrypt
    -0.08
    гон
    -0.08
    ogne
    -0.08
    หล
    -0.08
    æľ¬ç«Ļ
    -0.08
    POSITIVE LOGITS
    åIJĮè¡Į
    0.12
    åIJĮä¸ļ
    0.11
    类似çļĦ
    0.10
    æĥº
    0.10
    åIJĮäºĭ
    0.10
    spot
    0.10
    æŃĩ
    0.10
    缸äºĴ
    0.09
    pad
    0.09
    åł¡
    0.09
    Activations Density 0.046%

    No Known Activations