© 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. 1977
    Prev
    Next
    INDEX
    Explanations

    software license terms

    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
    æĩij
    -0.22
    çķĻè¨ĢæĿ¿
    -0.21
    æĺ³
    -0.21
     topp
    -0.20
     Noticed
    -0.20
    æįİ
    -0.20
    أسباب
    -0.20
    æijĩäºĨ
    -0.19
     sno
    -0.19
     francais
    -0.19
    POSITIVE LOGITS
    bery
    0.24
    :CGRect
    0.24
    acje
    0.23
     governing
    0.22
    <path
    0.22
    ]='\
    0.21
    },${
    0.20
    个交æĺĵ
    0.20
    =admin
    0.20
    ä¸ŃåĽ½ç½ij游
    0.20
    Activations Density 2.202%

    No Known Activations