© 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. 29649
    Prev
    Next
    INDEX
    Explanations

    Bejeweled, Noekeon, AIA, North Midland, iDream, Slither, Cheltenham, Fast, basolateral, Sails

    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
    ogan
    -0.07
    ifton
    -0.06
     thereof
    -0.06
    antz
    -0.06
    åĩ
    -0.06
    大èij±
    -0.06
    enance
    -0.06
    mvc
    -0.06
     Jacuzzi
    -0.06
    UNC
    -0.06
    POSITIVE LOGITS
    ½
    0.07
    ä¸ŃåĽ½åĮº
    0.07
    èĢħ为
    0.07
    kömm
    0.07
    æ§ĺãģª
    0.07
     sce
    0.07
     entero
    0.07
     scel
    0.06
    ilik
    0.06
    ĸ
    0.06
    Activations Density 0.513%

    No Known Activations