© 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. 50668
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    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
    ////////////////////////////////////////////////////////////////////////////
    -0.10
    ////////////////////////////////////////////////////
    -0.09
    ////////////////////////////////////////////////////////////////////////////////////////////////
    -0.09
    ////////////////////////////////////////////////////////////
    -0.09
    ////////////////////////////////////////////////////////////////
    -0.08
    ////////////////////////////////////////////////////////
    -0.08
    ়
    -0.08
    ////////////////////////////////////////////////
    -0.07
    ----------------------------------------------------------------------------
    -0.07
    ////////////////////////////////////////////////////////////////////////////////
    -0.07
    POSITIVE LOGITS
    èĩªå·±
    0.29
    èĩªå·±æ²¡æľī
    0.20
    èĩªå·±è¢«
    0.19
    odore
    0.18
    adays
    0.17
    etheless
    0.16
    gether
    0.14
    ostante
    0.14
    quoi
    0.13
    èĩªå·±èº«ä¸Ĭ
    0.13
    Activations Density 2.723%

    No Known Activations