© 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. 1898
    Prev
    Next
    INDEX
    Explanations

    are known

    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
     arguably
    -0.31
    ãģĵãģ¨ãģĮå¤ļãģĦ
    -0.24
    éļ¾æĢª
    -0.23
    éĻ¤éĿŀ
    -0.23
    .DialogInterface
    -0.23
     puzzled
    -0.22
    (ConfigurationManager
    -0.21
    æĬĹè¡¡
    -0.21
     pervasive
    -0.20
    vendors
    -0.20
    POSITIVE LOGITS
    0.30
     novitÃł
    0.28
    Translated
    0.26
     Horny
    0.26
    berra
    0.25
    aeda
    0.24
    /↵↵↵↵
    0.24
    öyle
    0.23
     Rigidbody
    0.23
     difficoltÃł
    0.23
    Activations Density 3.426%

    No Known Activations