© 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. 26350
    Prev
    Next
    INDEX
    Explanations

    foreign languages and technical terms

    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
    Rgb
    -0.08
    (Color
    -0.08
    çĨĬçĨĬ
    -0.08
    ä¹ĭæŃĮ
    -0.08
    TemplateName
    -0.08
    窩
    -0.08
    bergen
    -0.07
    ндÑĥ
    -0.07
     theoretically
    -0.07
     THEORY
    -0.07
    POSITIVE LOGITS
    æĸĩè¨Ģ
    0.11
    åı¤æĸĩ
    0.09
    ä¸İçݰ代
    0.09
    æĸĩè¨Ģæĸĩ
    0.09
    è¯Ń
    0.09
     syntax
    0.08
    ä¸Ńè¡Į
    0.08
    enj
    0.08
    åħ¸ç±į
    0.08
    åIJı
    0.07
    Activations Density 0.018%

    No Known Activations