© 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. 3793
    Prev
    Next
    INDEX
    Explanations

    GitHub content

    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
     ParseException
    -0.21
    TintColor
    -0.20
     Young
    -0.19
     Sach
    -0.19
    agy
    -0.19
    mak
    -0.18
     Bat
    -0.18
     Lim
    -0.18
     generado
    -0.18
    /../
    -0.18
    POSITIVE LOGITS
    çĦĮ
    0.21
    ç¡ķ士çłĶ究
    0.21
     Franken
    0.20
     ogóle
    0.20
    ãİŀ
    0.20
    ẫu
    0.20
    .githubusercontent
    0.20
    âĸį
    0.20
    ⾦
    0.20
    Çļ
    0.20
    Activations Density 0.009%

    No Known Activations