© 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. 3894
    Prev
    Next
    INDEX
    Explanations

    technical snippets

    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
    éĴĿ
    -0.21
    å®ĺæĸ¹å¾®ä¿¡
    -0.20
     showAlert
    -0.19
    variably
    -0.19
     caul
    -0.19
    Segue
    -0.19
    pé
    -0.19
    åĢŁéĴ±
    -0.19
    GLuint
    -0.18
    룰
    -0.18
    POSITIVE LOGITS
    ãİľ
    0.26
    说å®ŀ
    0.23
    åļĨ
    0.23
    çij¨
    0.22
    anka
    0.21
    iParam
    0.21
    ActionCreators
    0.21
     Após
    0.21
    tÃł
    0.21
     AssemblyVersion
    0.20
    Activations Density 0.003%

    No Known Activations