© 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. 13058
    Prev
    Next
    INDEX
    Explanations

    Indian, regex, out of bounds

    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
    ä¸İåĽ½éĻħ
    -0.07
    ÑĮÑİ
    -0.07
    رÙģت
    -0.06
    pond
    -0.06
    æĸ°å®ī
    -0.06
    _streams
    -0.06
    æĪIJç«ĭ以æĿ¥
    -0.06
    rosse
    -0.06
    好åIJĹ
    -0.06
    æĶ¯æµģ
    -0.06
    POSITIVE LOGITS
    variants
    0.08
     trunc
    0.08
    -money
    0.08
    åѦéĩij
    0.07
     Naturalmente
    0.07
     truncated
    0.07
    OutOfBounds
    0.07
    ::$
    0.07
    ateral
    0.07
    æĪª
    0.07
    Activations Density 0.004%

    No Known Activations