© 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. 3275
    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
     csak
    -0.23
     Matte
    -0.21
    âĪ®
    -0.20
    ustralian
    -0.20
     YT
    -0.20
    =\"$
    -0.19
    (DialogInterface
    -0.19
    cba
    -0.19
    usercontent
    -0.18
     ElseIf
    -0.18
    POSITIVE LOGITS
    afür
    0.23
    éĺħ读åħ¨æĸĩ
    0.22
    emetery
    0.22
    .isAuthenticated
    0.22
    interop
    0.21
    obierno
    0.21
    ptune
    0.20
    braska
    0.20
    è¿°èģĮ
    0.20
    家éĥ½çŁ¥éģĵ
    0.20
    Activations Density 0.001%

    No Known Activations