© 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. 1593
    Prev
    Next
    INDEX
    Explanations

    conditions or rules

    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
     «
    -0.42
     “
    -0.35
     "
    -0.34
     “âĢ¦
    -0.29
     ãĢĮ
    -0.27
     “[
    -0.25
     \"
    -0.25
    __":↵
    -0.25
     ``
    -0.25
    ãĢĮ
    -0.25
    POSITIVE LOGITS
    ”çļĦ
    0.37
    ”
    0.33
    oriously
    0.31
    ”ãĢĤ↵↵
    0.27
    ”ï¼Į
    0.26
    ãĢŀ
    0.26
    ãĢı
    0.25
    ãĢį
    0.24
     )↵↵↵↵↵↵↵↵
    0.23
     ".";↵
    0.23
    Activations Density 1.896%

    No Known Activations