© 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. 49172
    Prev
    Next
    INDEX
    Explanations

    academic paper introductions

    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
    ysz
    -0.07
    èĥĮä¸Ĭ
    -0.07
    ane
    -0.07
    old
    -0.07
     Tome
    -0.07
    æ°ij主
    -0.07
    udas
    -0.06
    erre
    -0.06
    _reload
    -0.06
    头
    -0.06
    POSITIVE LOGITS
    æİ¥ä¸ĭæĿ¥
    0.08
     situated
    0.07
     “[
    0.07
    æĬ¤çIJĨå·¥ä½ľ
    0.07
    æİ¥ä¸ĭæĿ¥çļĦ
    0.07
    setEnabled
    0.07
     Instances
    0.07
     admittedly
    0.07
    æľīå¿ħè¦ģ
    0.07
    ủng
    0.07
    Activations Density 0.145%

    No Known Activations