© 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. 3478
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    \<^
    -0.23
     }>
    -0.21
    opportunitÃł
    -0.21
     */,
    -0.20
     AppleWebKit
    -0.20
    ABI
    -0.20
    ={[
    -0.20
    __;
    -0.19
    *****↵↵
    -0.19
    HEST
    -0.19
    POSITIVE LOGITS
     ++)
    0.24
    utely
    0.22
    éĩįè¦ģåĽłç´ł
    0.20
    .EventQueue
    0.20
     UIF
    0.20
    |--------------------------------------------------------------------------↵
    0.20
     Tüm
    0.20
    ...");↵↵
    0.19
    åĨĻçļĦ
    0.19
    为主çļĦ
    0.19
    Activations Density 0.197%

    No Known Activations