© 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. 26914
    Prev
    Next
    INDEX
    Explanations

    parts of objects or concepts

    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
    çĥŃéŨæݨèįIJ
    -0.09
    ergestellt
    -0.08
    éľĵ
    -0.08
    _mr
    -0.07
    é£İåIJ¹è¿ĩ
    -0.07
    ploi
    -0.07
    cause
    -0.07
    à¸Ńà¸Ļุà¸įาà¸ķà¹ĥหà¹īà¸Ļำ
    -0.07
    constants
    -0.07
    æĺĵè´Ń
    -0.07
    POSITIVE LOGITS
     trib
    0.07
    rique
    0.07
    æľ¬æĿ¥
    0.06
    æĪĸèĢħ说
    0.06
     already
    0.06
    å§ĵ
    0.06
    æĻĵ
    0.06
    åİŁæľī
    0.06
    que
    0.06
     somehow
    0.06
    Activations Density 0.239%

    No Known Activations