© 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. 34269
    Prev
    Next
    INDEX
    Explanations

    longitudinal direction

    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
    agin
    -0.08
    åīįç½®
    -0.08
    aglia
    -0.07
     outright
    -0.07
    weiler
    -0.07
    æĿ¥èĩª
    -0.07
    ä¸įä¸ĭ
    -0.07
    -backend
    -0.07
    ared
    -0.07
    รà¸Ńà¸ļ
    -0.07
    POSITIVE LOGITS
    å¾Īéķ¿
    0.08
    è¶Ĭéķ¿
    0.08
    åij¨æľŁæĢ§
    0.07
    横åIJij
    0.07
    æĸ¹åIJijçļĦ
    0.07
    éķ¿éĿĴ
    0.07
     boyunca
    0.07
     sepanjang
    0.07
    orgot
    0.07
    ENTI
    0.07
    Activations Density 0.023%

    No Known Activations