© 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. 38796
    Prev
    Next
    INDEX
    Explanations

    digits in numerical sequences

    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
    rus
    -0.07
    (#)
    -0.07
    รั
    -0.07
    SPATH
    -0.07
    ниÑĤелÑĮ
    -0.07
    .Constant
    -0.06
    iker
    -0.06
    漫
    -0.06
    帶
    -0.06
    گرÛĮ
    -0.06
    POSITIVE LOGITS
    çļĦä¸Ģæł·
    0.07
    éĴ¥
    0.07
    -sync
    0.07
    acie
    0.07
    witz
    0.07
    åİ»è¿ĩ
    0.07
    ürg
    0.07
    elet
    0.07
    ölf
    0.07
    ä¸ĢåIJ¬
    0.07
    Activations Density 0.010%

    No Known Activations