© 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. 3497
    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
     withStyles
    -0.23
    Çļ
    -0.20
    åħ¨èµĦåŃIJ
    -0.20
    辿
    -0.20
    utilus
    -0.20
    ä¸Ģ个èģĮä¸ļ
    -0.20
    .Monad
    -0.20
    âĨĹ
    -0.19
    irlines
    -0.19
    usterity
    -0.19
    POSITIVE LOGITS
    olean
    0.23
    à¹ĭ
    0.21
    .getOwnProperty
    0.20
    "crypto
    0.19
    itm
    0.19
    chema
    0.18
    dit
    0.18
    izzie
    0.18
    ernational
    0.18
    -schema
    0.18
    Activations Density 0.000%

    No Known Activations