© 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. 40718
    Prev
    Next
    INDEX
    Explanations

    file types and content types

    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
     Concepts
    -0.08
    rovers
    -0.08
    ucia
    -0.08
     concepts
    -0.08
    иÑĤелÑĮÑģÑĤво
    -0.08
    yss
    -0.08
    å¼ķéĩı
    -0.07
    _lineno
    -0.07
    ooky
    -0.07
     imaginary
    -0.07
    POSITIVE LOGITS
     mime
    0.09
     formats
    0.09
     MIME
    0.09
     mimetype
    0.08
     fileType
    0.08
    /vnd
    0.08
    FileType
    0.08
    ç»ĵå°¾
    0.08
    æĸĩ件çļĦ
    0.08
     file
    0.08
    Activations Density 0.135%

    No Known Activations