© 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. 3605
    Prev
    Next
    INDEX
    Explanations

    technical or encoding

    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
    '&&
    -0.36
     ());↵↵
    -0.26
    %;"
    -0.25
    č↵↵
    -0.23
    éŃ
    -0.23
    #ac
    -0.21
    |h
    -0.21
     âĵĺ
    -0.21
    )||(
    -0.21
    >xpath
    -0.20
    POSITIVE LOGITS
    .KeyCode
    0.22
    ¿
    0.20
    inky
    0.19
     eof
    0.19
     eldest
    0.18
    stop
    0.18
     пÑĢаздник
    0.18
    resar
    0.18
    visit
    0.18
     favicon
    0.17
    Activations Density 0.001%

    No Known Activations