© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3803
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UClass
    -0.20
    weathermap
    -0.20
    pragma
    -0.20
    ="<<
    -0.20
    ):?>↵
    -0.19
    èĴ¯
    -0.19
    å¼Ľ
    -0.19
    ä¼Ĭæĭī
    -0.19
     Bashar
    -0.18
    åİĮ
    -0.18
    POSITIVE LOGITS
    /*@
    0.26
    serter
    0.22
    çĶŁäº§æĢ»åĢ¼
    0.22
    æĭľå¸ĪåѦèīº
    0.21
    	fflush
    0.20
    errupt
    0.20
    æĵ¤
    0.19
    nivers
    0.19
    .clipsToBounds
    0.19
    Networking
    0.19
    Activations Density 0.080%

    No Known Activations