© 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. 1843
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
     timespec
    -0.20
    两岸
    -0.20
    uner
    -0.20
     sür
    -0.19
    _nullable
    -0.19
    讵
    -0.18
     Vol
    -0.18
    ^
    -0.18
    aison
    -0.17
    ä¿Ŀåģ¥åĵģ
    -0.17
    POSITIVE LOGITS
    ornment
    0.33
    âĦī
    0.28
    çļĦ带é¢Ĩ
    0.27
     safeg
    0.24
    .EventQueue
    0.24
    .SDK
    0.23
     embod
    0.23
    )=='
    0.23
    )){↵↵
    0.23
    'email
    0.23
    Activations Density 0.257%

    No Known Activations