© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4125
    Prev
    Next
    INDEX
    Explanations

    0

    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
    Negative Logits
    puties
    -0.22
     ìľĦíķĺìŬ
    -0.21
    uminium
    -0.21
    /lgpl
    -0.21
     ofApp
    -0.20
    .getOwnProperty
    -0.20
    ertation
    -0.20
    Sharper
    -0.20
    æĥ³äºĨæĥ³
    -0.19
    ilogy
    -0.19
    POSITIVE LOGITS
    ä¸İæŶ
    0.21
    .Face
    0.21
    )↵↵↵↵↵↵↵↵
    0.21
    emsp
    0.20
    éĩĩçŁ¿çŃī
    0.19
    ofi
    0.19
    ÆĶ
    0.19
    ...");↵↵
    0.18
     Burnett
    0.18
    isor
    0.18
    Activations Density 0.010%

    No Known Activations