© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48597
    Prev
    Next
    INDEX
    Explanations

    copyright and license information

    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
    Ø©
    -0.14
    ation
    -0.12
    ness
    -0.11
    zung
    -0.10
    shire
    -0.10
    à§įস
    -0.10
    uum
    -0.09
    wai
    -0.09
    ----------------------------------------------------------------------
    -0.09
    ypse
    -0.09
    POSITIVE LOGITS
    a
    0.13
    ////////////
    0.13
    а
    0.13
    noinspection
    0.13
    ////////////////////////////////////////////////////////////////////////////
    0.12
    ////////////////////////////////////////////////////////////////
    0.12
    ////////////////////////////////////////////////////////
    0.12
    ////////////////////////////////////////////////////////////
    0.12
    s
    0.12
    ////////////////////////////////////////////////
    0.12
    Activations Density 0.153%

    No Known Activations