© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14934
    Prev
    Next
    INDEX
    Explanations

    both ... and

    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
    æīĢæľīè¿ĻäºĽ
    -0.10
    ä»»ä½ķåħ¶ä»ĸ
    -0.09
    æĺ¯ä¸ĢåĪĩ
    -0.09
     모ëĵł
    -0.09
     all
    -0.08
     itself
    -0.08
    à¸Ĺุà¸ģà¸Ħรัà¹īà¸ĩ
    -0.08
    à¸Ĺุà¸ģ
    -0.08
     another
    -0.08
    åħ¶ä¸İ
    -0.08
    POSITIVE LOGITS
    åIJĦèĩª
    0.17
    åIJĦèĩªçļĦ
    0.17
    åIJĦæľī
    0.14
    约èĢĮåIJĮ
    0.13
     одина
    0.12
    ä¸įåIJĮç¨ĭ度çļĦ
    0.11
    ä¸įåIJĮç¨ĭ度
    0.11
    åIJĦæľīåIJĦ
    0.11
    ãģĿãĤĮãģŀãĤĮ
    0.11
     respectively
    0.11
    Activations Density 0.165%

    No Known Activations