© 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. 15653
    Prev
    Next
    INDEX
    Explanations

    sets and sequences

    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
    ovem
    -0.08
    èµĦæĸĻä¸ĭè½½
    -0.08
    ersen
    -0.07
    em
    -0.07
    oes
    -0.07
    iales
    -0.07
    pheres
    -0.07
    value
    -0.07
    ä¸ĢåĬ¨ä¸įåĬ¨
    -0.06
    rakt
    -0.06
    POSITIVE LOGITS
     infinite
    0.07
    -ish
    0.07
    ListOf
    0.07
     Trot
    0.07
    EventManager
    0.07
     banyaknya
    0.07
    å¼ķ以为
    0.07
    ÑģÑİ
    0.07
    енÑĮ
    0.07
    ctic
    0.07
    Activations Density 0.002%

    No Known Activations