© 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. 14400
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    UT
    -0.07
    便æĺ¯
    -0.07
    interop
    -0.07
    ваÑĩ
    -0.07
    নি
    -0.07
     segreg
    -0.07
    imba
    -0.06
    夫åIJĽ
    -0.06
    oday
    -0.06
    ut
    -0.06
    POSITIVE LOGITS
    彩äºij
    0.07
     COP
    0.07
    æĭĨå¼Ģ
    0.07
    rous
    0.07
    entials
    0.07
    ÑİÑĢпÑĢи
    0.07
    'We
    0.07
     ÑĦоÑĢ
    0.07
    voices
    0.07
    å°ıæīĭ
    0.06
    Activations Density 0.004%

    No Known Activations