© 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. 1393
    Prev
    Next
    INDEX
    Explanations

    code and libraries

    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
    rippling
    -0.38
    preci
    -0.33
    uguay
    -0.31
    -football
    -0.31
    errupted
    -0.29
    âļĹ
    -0.29
    atég
    -0.28
    acerb
    -0.28
    riger
    -0.28
    icions
    -0.28
    POSITIVE LOGITS
     maç
    0.24
     móvil
    0.22
    smouth
    0.21
    very
    0.20
    ondrous
    0.20
    大家ä¸Ģèµ·
    0.20
     uomo
    0.20
     '{$
    0.20
     annum
    0.20
    æĤ¨çļĦåŃ©åŃIJ
    0.20
    Activations Density 8.897%

    No Known Activations