© 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. 3128
    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
    cxx
    -0.22
    欲
    -0.20
     AppRoutingModule
    -0.20
     CircularProgress
    -0.19
    æłĩè¯Ń
    -0.19
    genesis
    -0.18
    //*[
    -0.18
    èĨĬ
    -0.18
    ursal
    -0.18
    ardy
    -0.18
    POSITIVE LOGITS
    ĤŃ
    0.23
     winger
    0.21
    _<?
    0.20
    æįĥ
    0.20
    charted
    0.20
     Geschä
    0.19
    %!
    0.19
    rvine
    0.19
    alleries
    0.19
    éķ¶
    0.19
    Activations Density 0.002%

    No Known Activations