© 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. 13564
    Prev
    Next
    INDEX
    Explanations

    message, Article, string, cheese, Report, James

    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
     liá»ĩu
    -0.08
    apat
    -0.08
    墩
    -0.08
    apol
    -0.07
    usher
    -0.07
    åIJįæĢĿ
    -0.07
    æ·ĭ
    -0.07
    ç»ıæµİ带
    -0.07
    igon
    -0.07
    вÑĢа
    -0.07
    POSITIVE LOGITS
    ÙĤض
    0.07
    缸éĢ¢
    0.07
    çijķ
    0.07
    éĹ´éļĶ
    0.07
    rawer
    0.06
    zze
    0.06
    _skip
    0.06
    èĢĮå·²
    0.06
    座åı³
    0.06
     Thá»į
    0.06
    Activations Density 0.001%

    No Known Activations