© 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. 23171
    Prev
    Next
    INDEX
    Explanations

    code symbols and delimiters

    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
    å®
    -0.07
     OS
    -0.06
    лиÑģÑĮ
    -0.06
    nos
    -0.06
    FS
    -0.06
    lios
    -0.06
    ColumnType
    -0.06
     ES
    -0.06
    ij
    -0.06
    EW
    -0.06
    POSITIVE LOGITS
     susc
    0.08
    asher
    0.08
    å¾®ä¸į足
    0.07
    èī¯
    0.07
    মন
    0.07
    ubo
    0.07
    åįİé¾Ļ
    0.07
    Åijd
    0.07
    å®īçĦ¶
    0.07
    å£ĩ
    0.07
    Activations Density 0.179%

    No Known Activations