© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 274
    Prev
    Next
    INDEX
    Explanations

    science and math

    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
    ËĤ
    -0.22
     subtotal
    -0.21
     lowes
    -0.21
     Ebay
    -0.21
    ä¸įå±ŀäºİ
    -0.21
    ByUsername
    -0.20
    为主ä½ĵ
    -0.20
    aki
    -0.19
    æ³
    -0.19
     authService
    -0.19
    POSITIVE LOGITS
    /Dk
    0.38
    约为
    0.30
     nack
    0.27
    ç»ıéªĮåĢ¼
    0.27
    CompleteListener
    0.27
    "struct
    0.27
    大约
    0.26
    )arg
    0.25
    []>↵
    0.25
     erot
    0.25
    Activations Density 0.661%

    No Known Activations