© 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. 58057
    Prev
    Next
    INDEX
    Explanations

    winter holidays

    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
    ạt
    -0.07
    _TOO
    -0.06
    _TOUCH
    -0.06
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.06
    æ¯ķç«Ł
    -0.06
    é©
    -0.06
     offre
    -0.06
    åĽłä¸ºå®ĥ们
    -0.06
    etu
    -0.06
    aran
    -0.06
    POSITIVE LOGITS
    uluk
    0.08
    oust
    0.08
    urgia
    0.07
     terc
    0.07
    éĵģé¾Ļ
    0.07
    ivi
    0.07
    strup
    0.07
    æĽ¿å°¼
    0.07
    ilhar
    0.07
     bén
    0.07
    Activations Density 0.013%

    No Known Activations