© 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. 3215
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    âĢ¦↵↵↵↵
    -0.23
    deaux
    -0.21
     groupBox
    -0.21
    yyyyMMdd
    -0.21
    ä¸ĭä¸Ģç¯ĩ
    -0.20
    èĭĹ
    -0.20
    ä¸įçIJĨ
    -0.19
     Bundesliga
    -0.19
    licted
    -0.19
     inne
    -0.19
    POSITIVE LOGITS
    eldom
    0.24
    IFn
    0.24
     difficolt
    0.21
    angep
    0.21
    ervas
    0.20
    ynet
    0.20
    Verdana
    0.19
    }}>
    0.19
    AXB
    0.19
    _estimators
    0.19
    Activations Density 0.011%

    No Known Activations