© 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. 13880
    Prev
    Next
    INDEX
    Explanations

    18F-FDG PET

    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
    1
    -0.07
    -0.07
    user
    -0.07
    ue
    -0.07
    Y
    -0.07
    “
    -0.06
    á
    -0.06
    åľ¨ä¸İ
    -0.06
    ass
    -0.06
    is
    -0.06
    POSITIVE LOGITS
    instanc
    0.10
    idou
    0.09
    iction
    0.09
    ç»´æĸ¯
    0.09
    .grad
    0.09
     Kills
    0.09
     #__
    0.08
    ëĭ´
    0.08
    è°Īä¸įä¸Ĭ
    0.08
    ighbors
    0.08
    Activations Density 1.261%

    No Known Activations