© 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. 47931
    Prev
    Next
    INDEX
    Explanations

    code structures and data 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
    äºİä¸Ģ
    -0.07
    çģ¿
    -0.07
     knot
    -0.06
    zel
    -0.06
    äºĨå°ı
    -0.06
     Brenn
    -0.06
    ÑıÑĤи
    -0.06
    åIJijèį£
    -0.06
    ä¸Ģ女
    -0.06
    oth
    -0.06
    POSITIVE LOGITS
    iju
    0.08
    æįº
    0.07
    线çļĦ
    0.07
    æĭĺ
    0.07
    веÑĢо
    0.07
    ultipartFile
    0.07
    线
    0.07
    èĢĮåĩº
    0.07
    éĥµ
    0.07
    ätte
    0.07
    Activations Density 0.002%

    No Known Activations