© 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. 2951
    Prev
    Next
    INDEX
    Explanations

    t or /t

    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
    į°ìĿ´
    -0.26
    iếu
    -0.26
    ifestyles
    -0.25
    irteen
    -0.23
    клÑİÑĩа
    -0.22
    izzie
    -0.22
    inidad
    -0.21
    NullOr
    -0.21
    achable
    -0.21
    orough
    -0.21
    POSITIVE LOGITS
     )))
    0.23
    èħĺ
    0.22
     âĺĨ
    0.22
    ****↵
    0.22
     desar
    0.22
     nack
    0.21
    ifndef
    0.21
    ãİĿ
    0.21
     Aç
    0.21
    âĿĸ
    0.21
    Activations Density 0.139%

    No Known Activations