© 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. 2075
    Prev
    Next
    INDEX
    Explanations

    original

    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
    åIJĮæł·æĺ¯
    -0.21
    OCUS
    -0.20
    .GetService
    -0.19
    iad
    -0.19
    bsites
    -0.18
    âĺİ
    -0.18
    .GetItem
    -0.18
    vetica
    -0.18
    itzer
    -0.18
    emen
    -0.17
    POSITIVE LOGITS
     original
    0.88
    original
    0.74
     Original
    0.70
    åİŁ
    0.68
     originals
    0.66
    Original
    0.65
    åİŁæĿ¥çļĦ
    0.63
    åİŁå§ĭ
    0.61
    åİŁæľī
    0.59
    (original
    0.59
    Activations Density 0.729%

    No Known Activations