© 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. 57781
    Prev
    Next
    INDEX
    Explanations

    latitude and longitude coordinates

    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
    éģ
    -0.08
    æģ¶
    -0.07
    [strlen
    -0.07
    æĭĸ
    -0.06
    èĶij
    -0.06
    ä¹ı
    -0.06
    æ±Łåİ¿
    -0.06
    æĥ¡
    -0.06
    大åĵ¥
    -0.06
    erve
    -0.06
    POSITIVE LOGITS
    dá
    0.08
     [.
    0.08
     nau
    0.07
     abbr
    0.07
    inas
    0.07
     белÑĮ
    0.07
    Unhandled
    0.07
    _DOT
    0.07
    lio
    0.07
    ä¸įæĹ©
    0.07
    Activations Density 0.090%

    No Known Activations