© 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. 16575
    Prev
    Next
    INDEX
    Explanations

    merino | ATP | rail | link | forex | red | it

    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
     oblast
    -0.08
    åĮħéĩĮ
    -0.07
    ChangedEventArgs
    -0.07
    oreach
    -0.07
    .EMPTY
    -0.07
    cium
    -0.07
    astia
    -0.07
    bauer
    -0.07
    ä¹ĭ书
    -0.07
    )’
    -0.07
    POSITIVE LOGITS
    eram
    0.07
    æ¢
    0.07
    orts
    0.07
    eron
    0.07
    orong
    0.06
     trì
    0.06
     convention
    0.06
     ÑģвоÑij
    0.06
     McDon
    0.06
    skap
    0.06
    Activations Density 0.116%

    No Known Activations