© 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. 3918
    Prev
    Next
    INDEX
    Explanations

    special characters and non-latin scripts

    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
    以åıĬåIJĦç§į
    -0.07
    æľ¬èº«
    -0.07
     desco
    -0.07
    对åIJĦç§į
    -0.06
    verno
    -0.06
    validate
    -0.06
    schlä
    -0.06
    amani
    -0.06
    æľīè¯Ŀ
    -0.06
    ibes
    -0.06
    POSITIVE LOGITS
    æľŁä¸Ń
    0.08
    slashes
    0.07
     лиÑĪниÑħ
    0.07
    é¢Ŀå¤ĸçļĦ
    0.07
    åĭĿãģ¡
    0.07
    _vendor
    0.07
    nell
    0.07
    è¿ĻéĩĮçļĦ
    0.07
    ä¸ĬåĬł
    0.07
    åĬł
    0.06
    Activations Density 0.052%

    No Known Activations