© 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. 24505
    Prev
    Next
    INDEX
    Explanations

    time and configuration values

    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
    æĸĩåĮĸç¨ĭ度
    -0.08
    éŀ
    -0.08
    ificio
    -0.08
    Ñģно
    -0.07
    дÑĢ
    -0.07
    terior
    -0.07
    åĩºäºĨä¸Ģ
    -0.07
     ÐŀÐij
    -0.07
    /Private
    -0.07
    zos
    -0.07
    POSITIVE LOGITS
     Fre
    0.07
    FRE
    0.07
     fre
    0.07
     freedom
    0.07
    fre
    0.06
     Blan
    0.06
    _BOOT
    0.06
    åĭĥ
    0.06
     Bod
    0.06
     nowrap
    0.06
    Activations Density 0.001%

    No Known Activations