© 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. 4152
    Prev
    Next
    INDEX
    Explanations

    code and HTML

    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
    oproject
    -0.26
    LatLng
    -0.22
    arest
    -0.22
    odoxy
    -0.21
    matchCondition
    -0.21
    ãģĬå¾Ĺ
    -0.20
    BaseContext
    -0.20
    alem
    -0.20
    obook
    -0.20
    swers
    -0.20
    POSITIVE LOGITS
    *);↵↵
    0.22
     (![
    0.22
    İ·
    0.21
    &);↵↵
    0.21
    0.20
    raph
    0.20
    å¿Ŀ
    0.19
    aph
    0.19
     Crushers
    0.19
    游æĪıè§Ĵèī²
    0.19
    Activations Density 0.008%

    No Known Activations