© 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. 2753
    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
    chet
    -0.24
     Mattis
    -0.23
    æĬ¥ç¤¾
    -0.21
    æ®ĵ
    -0.21
    antha
    -0.21
    quist
    -0.20
    æ¯įæł¡
    -0.20
    ventas
    -0.20
     Fireplace
    -0.20
     Motorcycle
    -0.19
    POSITIVE LOGITS
    					↵					↵
    0.21
    _CODES
    0.20
     and
    0.20
    å¦Ĥæŀľçݩ家
    0.19
    Å·
    0.19
    aised
    0.19
    odable
    0.18
    åı¤åħ¸
    0.18
     by
    0.18
    Ļ¨
    0.18
    Activations Density 0.000%

    No Known Activations