© 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. 3187
    Prev
    Next
    INDEX
    Explanations

    technical context

    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
    duto
    -0.24
    ìĭľìĬ¤
    -0.23
    .scalablytyped
    -0.23
    ")));
    -0.23
    hế
    -0.22
    endance
    -0.22
    ')));↵↵
    -0.22
    娣
    -0.22
    erokee
    -0.22
    -fw
    -0.21
    POSITIVE LOGITS
    è¿ĶåĽŀæIJľçĭIJ
    0.20
     preco
    0.20
    å¢
    0.19
     authService
    0.19
     httpRequest
    0.18
    笳
    0.18
    èĭ±æł¼
    0.18
     reunion
    0.17
    ander
    0.17
    æģ¶æĦı
    0.17
    Activations Density 1.235%

    No Known Activations