© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21566
    Prev
    Next
    INDEX
    Explanations

    processes for preparation

    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
    occa
    -0.08
    rosa
    -0.08
    ë¡Ŀ
    -0.08
    PROTO
    -0.08
    istrator
    -0.08
    è¾¾æĸ¯
    -0.07
    åIJĿ
    -0.07
    æĭīå°Ķ
    -0.07
    spur
    -0.07
    unn
    -0.07
    POSITIVE LOGITS
    ially
    0.11
    EDURE
    0.10
    sweise
    0.09
    /process
    0.09
    ional
    0.08
    lez
    0.08
    ual
    0.08
    es
    0.08
    лÑĮÑİ
    0.08
    uale
    0.08
    Activations Density 0.075%

    No Known Activations