© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11390
    Prev
    Next
    INDEX
    Explanations

    death or end

    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
    ç¨Ķ
    -0.10
    éĴ¢æĿIJ
    -0.09
    .spacing
    -0.09
    åIJ¸å¼ķæĽ´å¤ļ
    -0.09
    åĴĮå®ĮåĸĦ
    -0.09
    heets
    -0.09
     remin
    -0.09
    FLT
    -0.09
    æµ®
    -0.08
    à´¤
    -0.08
    POSITIVE LOGITS
    åĨįä¹Łä¸į
    0.13
    åĨįä¹Ł
    0.13
    å°±æѤ
    0.12
    åīįéĢĶ
    0.12
    失åİ»äºĨ
    0.12
    ç»ĿæľĽ
    0.12
    å¿ħä¸įåı¯
    0.12
    ä»İæѤ
    0.11
    宣åijĬ
    0.11
     irre
    0.11
    Activations Density 0.088%

    No Known Activations