© 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. 41335
    Prev
    Next
    INDEX
    Explanations

    list.getChildAt

    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
    綱
    -0.08
    endido
    -0.07
     hab
    -0.07
    תר
    -0.06
    èĨĽ
    -0.06
    ecker
    -0.06
    endr
    -0.06
    åѦåłĤ
    -0.06
    ataires
    -0.06
    POSIT
    -0.06
    POSITIVE LOGITS
    缴æİ¥è¿Ľåħ¥
    0.08
    chnik
    0.08
    ìĶ©
    0.08
    UPI
    0.07
    è¿ĶåĽŀé¦ĸ页
    0.07
    aria
    0.07
    rial
    0.07
    æ´»çļĦ
    0.07
    æĺ¯æ¯ı个
    0.07
    ä¹ĭæºIJ
    0.07
    Activations Density 0.263%

    No Known Activations