© 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. 2903
    Prev
    Next
    INDEX
    Explanations

    strictness

    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
     )↵↵↵↵↵↵↵↵
    -0.25
    OffsetTable
    -0.23
    ,readonly
    -0.23
    bove
    -0.23
    æīĭèĦļ
    -0.21
    -scalable
    -0.20
    .shtml
    -0.20
     automáticamente
    -0.20
    "nil
    -0.20
     guarante
    -0.19
    POSITIVE LOGITS
    严
    0.23
     strict
    0.20
    ä¸¥æł¼çļĦ
    0.20
    ibus
    0.20
    _literal
    0.20
    éĴ¿
    0.20
    ä¸į论æĺ¯
    0.20
    ,application
    0.20
    严åİī
    0.19
     stricter
    0.19
    Activations Density 0.193%

    No Known Activations