© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 346
    Prev
    Next
    INDEX
    Explanations

    same similarly identical

    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
    ngr
    -0.23
    #ga
    -0.22
    nqu
    -0.22
    rary
    -0.22
    |=↵
    -0.22
    ssf
    -0.22
    .TRAILING
    -0.21
    toISOString
    -0.21
    ilmington
    -0.21
    ')."
    -0.21
    POSITIVE LOGITS
    åIJĮæł·çļĦ
    0.98
     same
    0.94
    缸åIJĮçļĦ
    0.93
    缸åIJĮ
    0.91
     similar
    0.89
    same
    0.84
    åIJĮæł·
    0.81
     identical
    0.79
    Same
    0.78
     similarly
    0.78
    Activations Density 3.049%

    No Known Activations