© 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. 16501
    Prev
    Next
    INDEX
    Explanations

    cast, sum, divisor, received, classification, expanded, function

    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
     Loch
    -0.07
    addir
    -0.07
    ½
    -0.07
    ustaka
    -0.07
    ÃģT
    -0.06
    Minor
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    emia
    -0.06
    )":
    -0.06
    uide
    -0.06
    POSITIVE LOGITS
     successfully
    0.08
     succesfully
    0.07
     correctly
    0.07
     processed
    0.07
    .updated
    0.07
    Å¡lo
    0.07
     Successfully
    0.07
    ẻ
    0.07
    æľ¬åĬŀæ³ķ
    0.07
    successfully
    0.07
    Activations Density 0.024%

    No Known Activations