© 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. 47402
    Prev
    Next
    INDEX
    Explanations

    milling mills

    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
    æļĸæļĸ
    -0.08
    æģ¯çļĦ
    -0.07
    水壶
    -0.07
    veloper
    -0.07
    Ñģловно
    -0.07
    åѦä¸ĵä¸ļ
    -0.07
    -proxy
    -0.07
    å¤ļçľĭ
    -0.07
    ×IJת
    -0.07
    .detach
    -0.07
    POSITIVE LOGITS
    è¯¾æľ¬
    0.08
    æĬĬäºĭæĥħ
    0.07
    å·¡
    0.07
    å°±ä¸ļæĮĩ导
    0.06
    uft
    0.06
    èĸĩ
    0.06
    ẻ
    0.06
    lyn
    0.06
    arbe
    0.06
    нома
    0.06
    Activations Density 0.013%

    No Known Activations