© 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. 2292
    Prev
    Next
    INDEX
    Explanations

    scientific text

    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
     )}↵↵
    -0.31
     todav
    -0.23
     embod
    -0.22
     {});↵↵
    -0.22
    .getOwnProperty
    -0.22
    ConverterFactory
    -0.22
    icom
    -0.21
     maneu
    -0.21
    ,Yes
    -0.21
    .EndsWith
    -0.21
    POSITIVE LOGITS
     var
    0.23
     sens
    0.22
    Mill
    0.20
    ç»ıèIJ¥æ´»åĬ¨
    0.20
    ude
    0.20
    ilit
    0.19
    icana
    0.19
    aryl
    0.19
    _accessor
    0.19
    ocratic
    0.19
    Activations Density 0.240%

    No Known Activations