© 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. 34280
    Prev
    Next
    INDEX
    Explanations

    code generation or data processing tasks

    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
    ÛĮÙĩ
    -0.07
    æĽ´åĬłå¼º
    -0.07
    è¡Įä¸ļæĸ°éĹ»
    -0.07
     Golk
    -0.07
    Ã¤ÃŁ
    -0.07
    agne
    -0.07
    empor
    -0.07
    磮
    -0.07
    ahan
    -0.07
    GENCY
    -0.07
    POSITIVE LOGITS
    æī¾åĩº
    0.07
    รà¸Ķ
    0.07
    æľĢç»ĪçļĦ
    0.07
    æľĢç»Ī
    0.07
    nder
    0.07
    å¦Ĥæŀľåı¯ä»¥
    0.07
     möglichst
    0.06
    ç¨Ģ
    0.06
    æ®Ĭ
    0.06
    æī¾åĪ°ä¸Ģ个
    0.06
    Activations Density 0.005%

    No Known Activations