© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4222
    Prev
    Next
    INDEX
    Explanations

    arbitrary symbols

    np_max-act-logits · gemini-2.5-flash-lite
    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
    Negative Logits
    oca
    -0.20
    è·
    -0.20
    .');
    -0.20
    utex
    -0.19
    .ut
    -0.19
    "},"
    -0.19
    .MaximizeBox
    -0.19
    à¸ļา
    -0.18
    utra
    -0.18
    ateful
    -0.18
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.25
     XYZ
    0.23
     اÙĦÙģÙĦ
    0.21
    ï¸
    0.20
    '=>['
    0.20
    è½µ
    0.20
    XXX
    0.20
     PORT
    0.20
    åı¯ä»¥æĽ´å¥½
    0.19
    åĽłåľ°
    0.19
    Activations Density 0.320%

    No Known Activations