© 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. 40976
    Prev
    Next
    INDEX
    Explanations

    code documentation delimiters

    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
    æѤè¡Į
    -0.07
     Pani
    -0.07
    å·²èİ·å¾Ĺ
    -0.07
    OSC
    -0.07
    å·²æĪIJåĬŁ
    -0.06
    主è¦ģ人åijĺ
    -0.06
    raw
    -0.06
    ono
    -0.06
    å·²æĪIJ
    -0.06
     DECLARE
    -0.06
    POSITIVE LOGITS
    WISE
    0.08
    atul
    0.07
    StyleSheet
    0.07
    EDE
    0.07
    æ±IJ
    0.07
    .$.
    0.07
    anya
    0.06
    ãģ¡ãģª
    0.06
     kald
    0.06
    ihad
    0.06
    Activations Density 0.001%

    No Known Activations