© 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. 4360
    Prev
    Next
    INDEX
    Explanations

    protest, demonstration

    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
    pat
    -0.21
    æī¿è®¤
    -0.20
     clearfix
    -0.19
    éĤ»éĩĮ
    -0.19
    InnerHTML
    -0.19
    ãİľ
    -0.18
    <pair
    -0.18
    æıIJæĭĶ
    -0.18
     peer
    -0.18
    èµ°å»Ĭ
    -0.18
    POSITIVE LOGITS
    \OptionsResolver
    0.26
     peacefully
    0.23
    æĬĹè®®
    0.23
    è¯īæ±Ĥ
    0.23
     seedu
    0.23
    demand
    0.22
    ç½¢
    0.22
    odox
    0.21
    èĩªåıij
    0.21
    ç¡ķ士çłĶ究
    0.21
    Activations Density 0.528%

    No Known Activations