© 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. 26156
    Prev
    Next
    INDEX
    Explanations

    originates from

    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
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.08
    åľ¨æīĢ
    -0.08
    åĬ³æĸ¯
    -0.08
    ẩn
    -0.08
    æĸ°éĹ»èĪĨæĥħ
    -0.08
    æľ¬ç¯ĩæĸĩç«ł
    -0.08
    æŀī
    -0.07
    urias
    -0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.07
    plin
    -0.07
    POSITIVE LOGITS
    èģĶ
    0.06
     L
    0.06
    豪
    0.06
     AIR
    0.06
     Jah
    0.06
    èģĶç½ij
    0.06
    æŁIJ个
    0.06
    undles
    0.06
     South
    0.06
     Ha
    0.06
    Activations Density 0.026%

    No Known Activations