© 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. 3929
    Prev
    Next
    INDEX
    Explanations

    technical or legal topics

    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
     errorCallback
    -0.21
    ParameterValue
    -0.20
    utzer
    -0.20
    顼
    -0.20
    æ¯Ķäºļ
    -0.20
    两家
    -0.19
    icy
    -0.19
    èĭ£
    -0.19
    *)((
    -0.18
     Kos
    -0.18
    POSITIVE LOGITS
    éĻ¢åī¯éĻ¢éķ¿
    0.23
    )new
    0.21
    hế
    0.20
    )(((
    0.20
    erguson
    0.20
    >tag
    0.19
     Explosion
    0.19
    ÑĥниÑĨип
    0.19
    .SelectCommand
    0.19
    )test
    0.19
    Activations Density 0.002%

    No Known Activations