© 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. 437
    Prev
    Next
    INDEX
    Explanations

    symbols/code

    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
    aeda
    -0.27
    éĵ©
    -0.24
     NavParams
    -0.22
     NUIT
    -0.22
     actionTypes
    -0.22
    ç½ijç«Ļé¦ĸ页
    -0.21
     "&#
    -0.21
    åŀŃ
    -0.21
    hores
    -0.21
     prive
    -0.21
    POSITIVE LOGITS
    '&&
    0.31
    :animated
    0.29
     UClass
    0.27
     embod
    0.24
     rekl
    0.24
    xda
    0.24
    !';↵
    0.23
     çĶŁåij½åij¨æľŁ
    0.23
    ;';↵
    0.23
    -Feb
    0.23
    Activations Density 2.121%

    No Known Activations