© 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. 20682
    Prev
    Next
    INDEX
    Explanations

    latex variable/symbol followed by punctuation

    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
    iale
    -0.07
    PPER
    -0.07
    åı¸
    -0.06
    өл
    -0.06
    erd
    -0.06
    éĩĩ访ä¸Ń
    -0.06
    mez
    -0.06
    .hstack
    -0.06
    arra
    -0.06
     дÑĭ
    -0.06
    POSITIVE LOGITS
    Ä©nh
    0.08
    åĢ©
    0.08
    enefit
    0.07
    uisse
    0.07
    ä¸įå®ļ
    0.07
    èħº
    0.07
    raft
    0.07
    .INTERNAL
    0.07
    以åIJİåĨį
    0.07
    avors
    0.07
    Activations Density 0.002%

    No Known Activations