© 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. 13833
    Prev
    Next
    INDEX
    Explanations

    defining a term

    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
    terie
    -0.09
    ħ
    -0.08
    ocie
    -0.08
    OfType
    -0.07
    /up
    -0.07
    ometown
    -0.07
    mue
    -0.07
    quote
    -0.07
    nheim
    -0.07
    OUS
    -0.07
    POSITIVE LOGITS
     coined
    0.09
    æīĢæĮĩ
    0.08
    ually
    0.08
    ical
    0.08
    /class
    0.07
    ç»Ŀ对çļĦ
    0.07
    plate
    0.07
    ÑĨ
    0.07
    åıĬåħ¶åºĶçĶ¨
    0.07
    گذارÛĮ
    0.07
    Activations Density 0.034%

    No Known Activations