© 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. 2533
    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
    hy
    -0.22
     hy
    -0.20
    该游æĪı
    -0.20
    ä¸Ģ个好çļĦ
    -0.19
     '%"
    -0.19
    çķĻåŃĺ
    -0.19
    .AddRange
    -0.19
    RIORITY
    -0.19
    絡
    -0.19
     bénéficie
    -0.19
    POSITIVE LOGITS
    :'.$
    0.24
    *sp
    0.23
    ');//
    0.23
    áIJī
    0.23
    zek
    0.22
    },č↵č↵
    0.22
    gó
    0.21
    ialized
    0.21
    cÃŃ
    0.21
    ='<?
    0.20
    Activations Density 0.001%

    No Known Activations