© 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. 4016
    Prev
    Next
    INDEX
    Explanations

    command line tools

    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
    .za
    -0.25
    ');↵↵↵↵
    -0.24
    åĽ½éĻħåľ¨çº¿
    -0.23
     NotSupportedException
    -0.20
     WARRANTIES
    -0.19
    .getOwnProperty
    -0.19
    -minus
    -0.19
    ãĥļãĥ³
    -0.19
    >((
    -0.19
    Vien
    -0.19
    POSITIVE LOGITS
    -cols
    0.20
    apo
    0.20
    è£Ķ
    0.19
    .dateFormat
    0.19
    idi
    0.18
     withRouter
    0.18
     OnClickListener
    0.18
    aneously
    0.18
    CTest
    0.18
    åĨĴ
    0.17
    Activations Density 0.015%

    No Known Activations