© 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. 45919
    Prev
    Next
    INDEX
    Explanations

    vector bundle, derivative, integrity, DR, duplicate, channel

    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
    æĸ¯é¡¿
    -0.09
    ól
    -0.08
    allah
    -0.08
    .createObject
    -0.08
    ļĮ
    -0.08
    é·
    -0.08
    OLF
    -0.07
    ponder
    -0.07
    ķĮ
    -0.07
    olla
    -0.07
    POSITIVE LOGITS
     нена
    0.08
    åľ¨æŁIJ
    0.07
    —if
    0.07
    omini
    0.07
    æŁIJä¸Ģ
    0.07
    ä¸İ被
    0.06
    æ´½
    0.06
    å·®ä¸į
    0.06
     Williamson
    0.06
    åĴĮ被
    0.06
    Activations Density 0.007%

    No Known Activations