© 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. 1997
    Prev
    Next
    INDEX
    Explanations

    technical terms or definitions

    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
    HING
    -0.25
    âĸį
    -0.25
    hiên
    -0.22
    ģını
    -0.22
    åİŁæĸĩåľ°åĿĢ
    -0.22
    âĸİ
    -0.21
    æ°ķ
    -0.21
    doch
    -0.21
    junction
    -0.20
    èĦ±é¢ĸèĢĮåĩº
    -0.20
    POSITIVE LOGITS
    ims
    0.20
    smarty
    0.20
    sis
    0.19
    彤
    0.19
    apia
    0.18
    coop
    0.18
    éļľ
    0.18
    å°±ç»Ļ大家
    0.18
     maç
    0.18
    .UTC
    0.18
    Activations Density 0.001%

    No Known Activations