© 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. 4383
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
     Uniform
    -0.20
     "");
    -0.20
     candid
    -0.20
     '');
    -0.19
     Hugh
    -0.19
     disappoint
    -0.19
     SLOT
    -0.19
    +offset
    -0.18
     resist
    -0.18
     brand
    -0.18
    POSITIVE LOGITS
     !");↵
    0.23
    !!");↵
    0.23
    ><![
    0.21
    åı¯æĥ³
    0.21
    è°ĪæģĭçĪ±
    0.21
     Melee
    0.21
    åŁ
    0.21
    -controls
    0.20
    ç¥
    0.20
    ".↵↵↵↵
    0.20
    Activations Density 0.057%

    No Known Activations