© 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. 3083
    Prev
    Next
    INDEX
    Explanations

    fox assets

    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
    SocketAddress
    -0.07
    rz
    -0.07
    _GRAPH
    -0.07
    æ¹Ľ
    -0.07
    ROL
    -0.06
    dzi
    -0.06
    èĬ±æľ¨
    -0.06
    scha
    -0.06
    ew
    -0.06
    _CLUSTER
    -0.06
    POSITIVE LOGITS
     excluding
    0.08
    excluding
    0.08
    ä¸įåĮħæĭ¬
    0.07
    åıĸåĨ³
    0.07
    åĮħæĭ¬äºĨ
    0.07
    éĻ¤å¤ĸ
    0.07
     ignoring
    0.07
     dian
    0.07
    umph
    0.07
    ota
    0.07
    Activations Density 0.038%

    No Known Activations