© 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. 46269
    Prev
    Next
    INDEX
    Explanations

    numbers and timestamps

    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
    utig
    -0.06
    ir
    -0.06
     doubles
    -0.06
    åľ¨
    -0.06
     scaleY
    -0.06
    odore
    -0.06
    andReturn
    -0.06
    er
    -0.06
     em
    -0.06
     fart
    -0.06
    POSITIVE LOGITS
    OUS
    0.09
    è¡ĮåĬ¨ä¸Ń
    0.09
    uiltin
    0.08
    гÑĸд
    0.08
    Subsystem
    0.08
    尼奥
    0.08
     ÙĨسب
    0.08
    zinho
    0.08
    orang
    0.07
    ntag
    0.07
    Activations Density 0.053%

    No Known Activations