© 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. 1630
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     licensors
    -0.24
    纰
    -0.23
    çļĦ带é¢Ĩ
    -0.22
    è¿ĶåĽŀæIJľçĭIJ
    -0.21
    mensagem
    -0.21
    _Texture
    -0.21
    çķĮ第ä¸Ģ
    -0.21
    åĺŀ
    -0.21
    buquerque
    -0.20
    .orange
    -0.20
    POSITIVE LOGITS
     ámb
    0.25
     dozen
    0.25
    okable
    0.23
    èł²
    0.23
     estimated
    0.22
     bieten
    0.22
     estimates
    0.21
    估计
    0.21
    ($('.
    0.21
    å·¦åı³
    0.21
    Activations Density 2.346%

    No Known Activations