© 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. 4272
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
     sh
    -0.24
    ÑĦе
    -0.21
    ,},↵
    -0.21
     ac
    -0.20
    .destroyAllWindows
    -0.20
     Ac
    -0.19
    æĺĬ
    -0.19
    ()}}↵
    -0.19
    (coeff
    -0.19
    .liferay
    -0.18
    POSITIVE LOGITS
    hare
    0.23
    ãĤĴè¶ħãģĪ
    0.23
    éĹ³
    0.22
    celain
    0.22
     pione
    0.21
     rematch
    0.21
     örg
    0.20
     suce
    0.20
     nrw
    0.20
     enthusi
    0.20
    Activations Density 0.337%

    No Known Activations