© 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. 60718
    Prev
    Next
    INDEX
    Explanations

    Listing information: bedrooms/bathrooms/sleeps

    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
    cia
    -0.07
    pic
    -0.06
    cze
    -0.06
    太ä¹ħ
    -0.06
    pb
    -0.06
    cza
    -0.06
    |[
    -0.06
    coon
    -0.06
    ensis
    -0.06
    ugi
    -0.06
    POSITIVE LOGITS
     altrett
    0.07
    åĪĨç«Ļ
    0.07
    Dirs
    0.07
    клей
    0.07
    ultan
    0.07
    çİ©çİ©
    0.07
    æĽ¾è¡¨ç¤º
    0.07
     slips
    0.07
    CTX
    0.07
    fix
    0.06
    Activations Density 0.017%

    No Known Activations