© 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. 29293
    Prev
    Next
    INDEX
    Explanations

    Burma, Roman Empire

    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
    èĢĮå°±
    -0.08
    èĢĮ代ä¹ĭ
    -0.06
     deb
    -0.06
    unga
    -0.06
    èĢĮæľª
    -0.06
    istus
    -0.06
     something
    -0.06
    )((((
    -0.06
    èĹ
    -0.06
     doc
    -0.06
    POSITIVE LOGITS
    åıĪ称
    0.21
     aka
    0.21
    ä¹Łåı«
    0.21
    åıĪåı«
    0.21
    ä¹Łç§°
    0.20
    ä¹Łå°±æĺ¯
    0.20
    ä¹Łç§°ä¸º
    0.20
    åıĪ称为
    0.19
    åıĪåIJį
    0.19
    ä¿Ĺ称
    0.17
    Activations Density 1.087%

    No Known Activations