© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
    .epam
    -0.24
    zerbai
    -0.21
    macen
    -0.20
    çľ©
    -0.20
    åĪ©çĶ¨æĤ¨çļĦ
    -0.20
    åľ¨é¦Ļ港
    -0.20
    ноп
    -0.20
    ðŁĺģ
    -0.20
    езн
    -0.20
    itere
    -0.20
    POSITIVE LOGITS
    nonnull
    0.22
     Wrest
    0.21
    çģµ
    0.20
    upplier
    0.20
     Hitch
    0.19
    LOSS
    0.18
    æīĢåľ¨
    0.18
    å¿ĥ缮ä¸Ń
    0.18
    ä¾ĽåºĶ
    0.18
    ];↵↵↵
    0.18
    Activations Density 0.001%

    No Known Activations