© 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. 3708
    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
    erty
    -0.22
    æĥ¯
    -0.20
    -0.20
    æĥħæĻ¯
    -0.19
    ujet
    -0.19
    Seleccione
    -0.19
     "
    -0.19
    OCUMENT
    -0.18
     -
    -0.18
    å®ŀ
    -0.18
    POSITIVE LOGITS
    âļĹ
    0.28
    صÙĨد
    0.28
    âĮĤ
    0.26
    âĹĤ
    0.26
    ðŁĵIJ
    0.25
    ä¼łå¥ĩ游æĪı
    0.25
     авг
    0.24
    ÙĨÙħÙĪØ°
    0.23
    /MPL
    0.23
    __;
    0.22
    Activations Density 0.000%

    No Known Activations