© 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. 50585
    Prev
    Next
    INDEX
    Explanations

    circuit court citations

    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
    _CPP
    -0.07
    rowse
    -0.06
     Desa
    -0.06
     Stad
    -0.06
     Ashe
    -0.06
     Newtown
    -0.06
    åĽ½å®¶åĴĮ
    -0.06
     Nación
    -0.06
    æĸ°æĿIJæĸĻ
    -0.06
    (CH
    -0.06
    POSITIVE LOGITS
    IDA
    0.08
    jab
    0.08
    fus
    0.07
    supported
    0.07
    antine
    0.07
    æľīè¾ĥ强çļĦ
    0.07
    eci
    0.07
    ãĥįãĤ¹
    0.07
    èĹ»
    0.07
    æŶéļĶ
    0.07
    Activations Density 0.633%

    No Known Activations