© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1039
    Prev
    Next
    INDEX
    Explanations

    of

    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
    è°µ
    -0.28
     sublicense
    -0.26
    -transitional
    -0.26
     acompaña
    -0.25
     franca
    -0.25
    é¾Į
    -0.25
     Ñģдела
    -0.24
    icensing
    -0.24
    çĿ¥
    -0.23
     RequestMethod
    -0.23
    POSITIVE LOGITS
    æīĢæīĢ
    0.31
    ä½Ĩä¸įéĻIJ
    0.30
    æĢ§ä»·
    0.29
     non
    0.28
    éģ´
    0.28
    å§Ķç»Ħç»ĩ
    0.27
    æĤ¨åIJĮæĦı
    0.25
    cestor
    0.25
    /↵↵↵↵
    0.25
    æĿ¥çľĭçľĭåIJ§
    0.24
    Activations Density 11.548%

    No Known Activations