© 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. 26012
    Prev
    Next
    INDEX
    Explanations

    research and researchers

    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
    ogramm
    -0.09
    åѦå¾Ĺ
    -0.08
    apprent
    -0.08
    _stdio
    -0.08
    å¾·éŁ³
    -0.08
    å½¢èī²
    -0.07
    à¹Īาย
    -0.07
    amanca
    -0.07
     revit
    -0.07
    èīºèĢĥ
    -0.07
    POSITIVE LOGITS
     research
    0.11
    ç§ijçłĶ
    0.10
     scientific
    0.09
    ä¸İçłĶ究
    0.09
    วิà¸Īัย
    0.09
    çłĶ究çļĦ
    0.09
    research
    0.08
     Research
    0.08
    ç§ijçłĶå·¥ä½ľ
    0.08
    åĴĮçłĶ究
    0.08
    Activations Density 0.190%

    No Known Activations