© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1005
    Prev
    Next
    INDEX
    Explanations

    exponentiation

    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
    èIJĬ
    -0.22
     UnityEditor
    -0.21
    èݱ
    -0.20
    太åŃIJ
    -0.20
    å¿ĥ仪
    -0.20
     previews
    -0.19
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.19
     QModelIndex
    -0.18
    èIJ½åĪ°
    -0.18
    uld
    -0.18
    POSITIVE LOGITS
    ²
    0.29
     squared
    0.28
     fkk
    0.27
    cuador
    0.22
    .pow
    0.21
    rawtypes
    0.21
    *****↵↵
    0.21
     "></
    0.21
    æģ¹
    0.20
    ä¸ī次
    0.20
    Activations Density 0.294%

    No Known Activations