© 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. 3977
    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
     under
    -0.21
    骢
    -0.20
    æŨ
    -0.20
    éħ´
    -0.18
    .DrawLine
    -0.18
     recently
    -0.18
     possibilities
    -0.17
    licht
    -0.17
    åIJı
    -0.17
    vern
    -0.17
    POSITIVE LOGITS
     Según
    0.27
    ómo
    0.25
    esModule
    0.23
     italiane
    0.23
     ));č↵
    0.22
     Erotic
    0.21
    ële
    0.21
     multer
    0.21
     Parenthood
    0.21
    éĢ¯
    0.20
    Activations Density 0.000%

    No Known Activations