© 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. 3724
    Prev
    Next
    INDEX
    Explanations

    health and medicine

    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
    -alist
    -0.21
    либо
    -0.21
    >Nama
    -0.21
    !");
    -0.20
    åĭł
    -0.20
    ect
    -0.19
    ].'
    -0.19
    ±
    -0.19
     CAUSED
    -0.19
    .VisualStudio
    -0.19
    POSITIVE LOGITS
     apparently
    0.24
     Apparently
    0.22
    .utilities
    0.21
    Apparently
    0.20
     not
    0.20
     even
    0.19
    hotmail
    0.19
     Spi
    0.19
    .Imp
    0.19
    (QStringLiteral
    0.19
    Activations Density 0.341%

    No Known Activations