© 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. 3503
    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
    >(*
    -0.20
    uptools
    -0.20
     HtmlWebpackPlugin
    -0.20
    马
    -0.19
     },{↵
    -0.19
    *>(&
    -0.18
    åľ¨èģĮ
    -0.18
     jMenuItem
    -0.18
    roid
    -0.18
    edBy
    -0.18
    POSITIVE LOGITS
     èĩªåĬ¨çĶŁæĪIJ
    0.22
    trys
    0.22
    ilmiÅŁ
    0.22
    èĻĵ
    0.21
    .shiro
    0.21
    (TimeSpan
    0.20
    æ¯ıä¸Ģ天
    0.20
    typings
    0.20
    beits
    0.20
    createForm
    0.20
    Activations Density 0.000%

    No Known Activations