© 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. 2568
    Prev
    Next
    INDEX
    Explanations

    Italian origin

    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
    oproject
    -0.24
    logan
    -0.24
    uai
    -0.23
    ï·º
    -0.23
    #ab
    -0.23
    IRTUAL
    -0.21
     tac
    -0.21
    eah
    -0.20
    ynos
    -0.20
    itational
    -0.20
    POSITIVE LOGITS
     italiane
    0.21
    rement
    0.19
    ¥
    0.19
    飧
    0.18
    áIJī
    0.18
    KHTML
    0.18
    AdminController
    0.18
    ä»ĭ
    0.18
    åĨ³ä¸į
    0.18
    bellion
    0.17
    Activations Density 0.004%

    No Known Activations