© 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. 2530
    Prev
    Next
    INDEX
    Explanations

    means or passage

    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
    thinkable
    -0.30
    :animated
    -0.24
    *)_
    -0.23
    "is
    -0.21
    inema
    -0.20
    'http
    -0.20
    -peer
    -0.20
    isnan
    -0.20
    ptune
    -0.20
    .isVisible
    -0.19
    POSITIVE LOGITS
     via
    0.75
    éĢļè¿ĩ
    0.70
    via
    0.63
     bằng
    0.59
    éĢļè¿ĩ对
    0.58
     using
    0.58
     through
    0.57
    åı¯éĢļè¿ĩ
    0.54
    using
    0.54
     mediante
    0.54
    Activations Density 1.643%

    No Known Activations