© 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. 1350
    Prev
    Next
    INDEX
    Explanations

    evidence

    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
    iÄŁi
    -0.23
    *pow
    -0.22
    unprocessable
    -0.22
    å²Ļ
    -0.22
    çļĦè¯Ŀé¢ĺ
    -0.21
    *Math
    -0.21
    åĹĮ
    -0.21
    èı¹
    -0.20
    åıĺåİĭ
    -0.20
    çļĦåħ³æ³¨
    -0.19
    POSITIVE LOGITS
    è¯ģæį®
    0.47
     evidence
    0.47
    è¯ģå®ŀ
    0.36
    ç»ĵ论
    0.35
     Evidence
    0.34
     supporting
    0.32
    è¯ģæĺİ
    0.32
    åı¯ä¿¡
    0.31
     facts
    0.29
    è¯ģ
    0.29
    Activations Density 2.242%

    No Known Activations