© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1641
    Prev
    Next
    INDEX
    Explanations

    extra data

    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
    .sendStatus
    -0.24
    owler
    -0.22
    declspec
    -0.21
    æĶ¹éĿ©å§Ķ
    -0.20
    åīįæĿ¥
    -0.19
    _BORDER
    -0.19
    èłĸ
    -0.19
    ora
    -0.19
    :invoke
    -0.19
    getMethod
    -0.18
    POSITIVE LOGITS
     Extra
    0.28
    data
    0.27
    Extra
    0.27
     Extras
    0.25
    extra
    0.25
     data
    0.25
     extras
    0.24
     extra
    0.24
    paque
    0.24
    _drvdata
    0.24
    Activations Density 0.453%

    No Known Activations