© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60267
    Prev
    Next
    INDEX
    Explanations

    predicts signatures and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĪªç«Ļ
    -0.08
    à¸ļัà¸į
    -0.07
    建ç«Ļ
    -0.07
    سÙĪب
    -0.07
    воÑĢÑı
    -0.07
    è¡Į使
    -0.07
     اض
    -0.06
    ä¸Ģä½ľ
    -0.06
    .bz
    -0.06
    /Foundation
    -0.06
    POSITIVE LOGITS
    é¢ĦæľŁ
    0.11
    çļĦé¢ĦæľŁ
    0.11
    çļĦçIJĨ论
    0.10
    é¢ĦæľŁçļĦ
    0.10
     predictions
    0.10
     expected
    0.10
    é¢Ħè¨Ģ
    0.10
    é¢Ħè®¡åľ¨
    0.10
    çIJĨ论
    0.09
    expected
    0.09
    Activations Density 0.104%

    No Known Activations