© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 206
    Prev
    Next
    INDEX
    Explanations

    all

    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
    exampleModal
    -0.23
    myModal
    -0.22
    eneg
    -0.22
    ThemeProvider
    -0.21
    esteem
    -0.21
    تذÙĥر
    -0.20
     ++)↵
    -0.20
    uegos
    -0.20
    inati
    -0.20
     Kurd
    -0.20
    POSITIVE LOGITS
    igator
    0.33
    owing
    0.32
     sorts
    0.31
    /all
    0.31
    iteration
    0.30
    uring
    0.30
     demás
    0.30
    _except
    0.29
     except
    0.28
    uded
    0.28
    Activations Density 0.885%

    No Known Activations