© 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. 60756
    Prev
    Next
    INDEX
    Explanations

    technical configuration files

    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
    icke
    -0.07
    åĽ½äºº
    -0.06
    -than
    -0.06
    ÑĮÑı
    -0.06
    oby
    -0.06
    rous
    -0.06
    eny
    -0.06
    avance
    -0.06
    è¡Ĺåı£
    -0.06
    anded
    -0.06
    POSITIVE LOGITS
    udeau
    0.07
    åħ°çī¹
    0.07
    ниÑĨ
    0.07
    åĴĮèĩªå·±çļĦ
    0.07
    æĸ°ç¤¾
    0.07
    uluh
    0.07
    ben
    0.07
    usel
    0.07
    ccount
    0.07
    bot
    0.07
    Activations Density 0.017%

    No Known Activations