© 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. 42988
    Prev
    Next
    INDEX
    Explanations

    software engineering and technology

    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
    ä¸ĭè§Ĵ
    -0.07
    amerika
    -0.07
    isé
    -0.07
    ç´ļçļĦ
    -0.06
    icales
    -0.06
    izada
    -0.06
    imos
    -0.06
    anness
    -0.06
    edException
    -0.06
    amen
    -0.06
    POSITIVE LOGITS
    .constructor
    0.08
    çIJĨ论çłĶ究
    0.08
    çIJĨ论
    0.08
    ä½ĵ系建设
    0.08
    ç«Ļç«Ļ
    0.07
    çIJĨ论åĴĮ
    0.07
    天å°Ĭ
    0.07
    elman
    0.07
     Everywhere
    0.07
    è¦ģ说
    0.07
    Activations Density 0.300%

    No Known Activations