© 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. 65357
    Prev
    Next
    INDEX
    Explanations

    function calls with single letter arguments

    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
    åħ¶ä¸Ń以
    -0.07
    对äºĨ
    -0.07
    æŃ»ä¸į
    -0.07
    å·²ç»ıä¸įæĺ¯
    -0.06
    olest
    -0.06
    çļĦä¸įèī¯
    -0.06
    åij¨åĪ°çļĦ
    -0.06
    Ī¬
    -0.06
    åĿį
    -0.06
    ij¸
    -0.06
    POSITIVE LOGITS
    èIJ¦
    0.10
    çıĬ
    0.08
    éģŃ
    0.07
    ObjectName
    0.07
    ervas
    0.07
    ç¬Ļ
    0.07
    apan
    0.07
    åĽ´æ£ĭ
    0.07
    blood
    0.07
    èķĥ
    0.07
    Activations Density 0.085%

    No Known Activations