© 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. 4074
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    çļĦ带é¢Ĩ
    -0.23
    .firebaseapp
    -0.23
    },č↵č↵
    -0.21
     scaleY
    -0.20
    /↵↵↵↵
    -0.20
    urd
    -0.19
    صØŃ
    -0.19
     af
    -0.19
    游æĪıæĵįä½ľ
    -0.18
    åĿļå®ļä¸į移
    -0.18
    POSITIVE LOGITS
    ')."
    0.24
    (QStringLiteral
    0.21
     Pics
    0.21
    noc
    0.20
    Salvar
    0.20
    repid
    0.19
     onBlur
    0.19
    =""/>↵
    0.19
     Favor
    0.19
     Redistributions
    0.19
    Activations Density 0.076%

    No Known Activations