© 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. 2543
    Prev
    Next
    INDEX
    Explanations

    structured content

    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
    iage
    -0.23
    __;
    -0.23
    -lnd
    -0.23
    ãĥµ
    -0.23
    _EOL
    -0.23
    Äĩe
    -0.22
    +","+
    -0.22
    herits
    -0.22
    urnished
    -0.22
    FormsModule
    -0.21
    POSITIVE LOGITS
    ederland
    0.21
    è´£ç¼ĸ
    0.20
    o
    0.19
    RoleId
    0.19
     sober
    0.19
    大å®Ĺ
    0.19
    baugh
    0.18
     Valle
    0.18
     caul
    0.18
     outputPath
    0.18
    Activations Density 0.001%

    No Known Activations