© 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. 32785
    Prev
    Next
    INDEX
    Explanations

    bilinear transform, reimann sphere

    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
    rael
    -0.07
    ooth
    -0.07
    bon
    -0.07
     Pellegr
    -0.06
    зеÑĢ
    -0.06
    åĩºå·®
    -0.06
    uppe
    -0.06
    ingg
    -0.06
    IBUT
    -0.06
    é¼İ缼
    -0.06
    POSITIVE LOGITS
    íıIJ
    0.08
     sầu
    0.08
    çŃ¹
    0.07
    itches
    0.07
    èĴĤ
    0.07
    ãģ²ãģ¨
    0.07
    cze
    0.07
    verläss
    0.07
    tev
    0.07
    ards
    0.07
    Activations Density 0.002%

    No Known Activations