© 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. 13695
    Prev
    Next
    INDEX
    Explanations

    code function calls

    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
    容
    -0.07
    计çļĦ
    -0.06
    èIJ½
    -0.06
     оÑĤм
    -0.06
     Fallon
    -0.06
     Depot
    -0.06
    æĭĹ
    -0.06
    ä¸įè¿ĩæĿ¥
    -0.06
    åĢĻ
    -0.06
    è¯Ŀ
    -0.06
    POSITIVE LOGITS
    _globals
    0.09
    ights
    0.08
    irut
    0.08
    ãĤ¥
    0.08
    esda
    0.08
    ProgressBar
    0.08
    .running
    0.08
    пÑĢÑĥ
    0.08
    ÑĤинг
    0.08
    é¢Ħç¥Ŀ
    0.07
    Activations Density 0.001%

    No Known Activations