© 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. 2246
    Prev
    Next
    INDEX
    Explanations

    descriptive terms

    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
    ombine
    -0.23
    ç»Ļåĩº
    -0.21
    CanBe
    -0.21
    entiful
    -0.20
    izabeth
    -0.20
    lycer
    -0.20
    ilmington
    -0.19
    reative
    -0.19
     TMPro
    -0.19
    ubbo
    -0.19
    POSITIVE LOGITS
     opportunity
    0.28
    æľºä¼ļ
    0.27
    çļĦæľºä¼ļ
    0.26
     opportunities
    0.24
    %X
    0.23
    å¥ijæľº
    0.22
    PA
    0.22
    means
    0.21
     {{--<
    0.21
     bridge
    0.21
    Activations Density 0.331%

    No Known Activations