© 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. 2905
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    }\.[
    -0.25
    ;');↵
    -0.24
    ospace
    -0.24
    >NN
    -0.24
     ?>↵↵↵
    -0.23
    ðŁĵIJ
    -0.23
    /↵↵↵↵
    -0.22
    assador
    -0.22
    rowable
    -0.22
    ebin
    -0.22
    POSITIVE LOGITS
     createDate
    0.19
    -thumbnail
    0.19
     setAddress
    0.19
    家åĬ¡
    0.19
    .SQL
    0.18
     заÑīиÑĤ
    0.18
    .URI
    0.18
    oble
    0.18
    æĭ±
    0.18
    -toggler
    0.18
    Activations Density 0.001%

    No Known Activations