© 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. 62318
    Prev
    Next
    INDEX
    Explanations

    ejs or numbers

    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
     
    -0.07
    usat
    -0.07
    æĽ½
    -0.07
    imak
    -0.07
    ä¸Ģå¸Ĩ
    -0.07
    ôn
    -0.07
    æĸ°çĶŁæ´»
    -0.07
    мÑı
    -0.07
    æīĭæĭ¿
    -0.07
    è¯ģæį®è¯ģæĺİ
    -0.07
    POSITIVE LOGITS
    åĬ¡
    0.07
    ctor
    0.07
    avid
    0.07
    åİŁåĪĻä¸Ĭ
    0.07
    éĽ
    0.07
    ÑĴе
    0.07
    ipan
    0.07
    .localization
    0.07
    ugi
    0.07
    mith
    0.06
    Activations Density 0.076%

    No Known Activations