© 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. 2376
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ofApp
    -0.27
    /Dk
    -0.26
     )↵↵↵↵↵↵↵↵
    -0.24
     Specialty
    -0.23
     rekl
    -0.23
     asia
    -0.22
     èĩªåĬ¨çĶŁæĪIJ
    -0.22
    )init
    -0.21
     Xperia
    -0.21
    ignKey
    -0.21
    POSITIVE LOGITS
    GridColumn
    0.22
     bytearray
    0.21
    ocache
    0.21
    åķĨæĬ¥
    0.19
    代çIJĨ人
    0.19
    abd
    0.19
    è´¥
    0.19
    oya
    0.18
     et
    0.18
    rio
    0.18
    Activations Density 0.000%

    No Known Activations