© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1027
    Prev
    Next
    INDEX
    Explanations

    specific identifiers

    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
    coholic
    -0.25
    istent
    -0.21
     Alicia
    -0.20
     sle
    -0.20
    patibility
    -0.20
    âĦ
    -0.19
     IRepository
    -0.18
    å¿Ŀ
    -0.18
    [Boolean
    -0.18
    ç¾Ĭæ¯Ľ
    -0.18
    POSITIVE LOGITS
    libft
    0.23
     Publié
    0.23
    å°±æĿ¥çľĭçľĭ
    0.20
    åħ¨èµĦåŃIJ
    0.20
    çĶŁæĢģåľĪ
    0.20
    ornings
    0.20
    æĪijçļĦå¿ĥ
    0.19
    };č↵č↵č↵
    0.19
    è¿ĶåĽŀæIJľçĭIJ
    0.19
     $('#'
    0.19
    Activations Density 0.002%

    No Known Activations