© 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. 3454
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    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
    #ac
    -0.23
    !=(
    -0.22
     ?>↵↵↵
    -0.20
    ä¿IJ
    -0.19
    ynos
    -0.19
    Vien
    -0.19
    .gnu
    -0.18
    вал
    -0.18
    æ°Ķè¡Ģ
    -0.18
    åİĨåı²æĸ°
    -0.18
    POSITIVE LOGITS
    extrême
    0.23
    .git
    0.21
    /src
    0.20
    RYPTO
    0.20
    æĸĩåĮĸä¼łåªĴ
    0.20
    atinum
    0.19
    Türkiye
    0.19
    TagName
    0.19
    izr
    0.19
     }č↵č↵č↵č↵
    0.19
    Activations Density 0.406%

    No Known Activations