© 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. 51132
    Prev
    Next
    INDEX
    Explanations

    standpoint, period, localized, concerns, engage, possesses, arranged

    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
    éĢļè¿ĩ以ä¸Ĭ
    -0.09
    phinx
    -0.09
    èIJ¥éĢłèī¯å¥½
    -0.09
    åIJĮä¸Ĭ
    -0.09
    ondi
    -0.08
    ä¸įåı¯èĥ½çļĦ
    -0.08
     bigger
    -0.08
    ä»ĸå°±æĺ¯
    -0.08
    ä¸įèĥ½åIJĥ
    -0.08
    idth
    -0.08
    POSITIVE LOGITS
     sogenannten
    0.09
     sogenannte
    0.08
     **
    0.07
    Ùĭ
    0.07
    åijĪçİ°åĩº
    0.07
    ãģĦãĤıãĤĨãĤĭ
    0.07
     notably
    0.07
     prominently
    0.06
    åħ·æľī以ä¸ĭ
    0.06
    æĭ¶
    0.06
    Activations Density 0.204%

    No Known Activations