© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3963
    Prev
    Next
    INDEX
    Explanations

    NOT

    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
     депÑĥÑĤ
    -0.21
    icerca
    -0.21
    usterity
    -0.20
    nç
    -0.20
    FUN
    -0.19
    (iOS
    -0.19
    _strlen
    -0.19
    润æ»ij
    -0.18
    };č↵č↵č↵
    -0.18
     Ksi
    -0.18
    POSITIVE LOGITS
     manual
    0.27
    Manual
    0.26
     Manual
    0.24
    æīĭåĬ¨
    0.23
    âĤĵ
    0.23
     ettiÄŁi
    0.22
     manually
    0.22
    åĬ¨æīĭ
    0.21
    åĬ¨
    0.21
    åĭ¿
    0.20
    Activations Density 0.069%

    No Known Activations