© 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. 4327
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
    благо
    -0.23
    toDate
    -0.22
    .CompareTag
    -0.22
    æĸ°æµªè´¢ç»ı
    -0.20
     IonicModule
    -0.20
    illet
    -0.19
    ÅŁehir
    -0.19
    ÐŁÐµÑĤеÑĢбÑĥÑĢ
    -0.18
    cancellationToken
    -0.18
    :maj
    -0.18
    POSITIVE LOGITS
     +=↵
    0.25
     Recap
    0.23
    ./(
    0.23
     è¾ĵ
    0.22
    linkplain
    0.21
    FOUNDATION
    0.21
    GORITH
    0.20
    iel
    0.20
     CONTRIBUTORS
    0.19
    (fabs
    0.19
    Activations Density 0.588%

    No Known Activations