© 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. 1971
    Prev
    Next
    INDEX
    Explanations

    solution

    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
     spécialisé
    -0.22
    orderby
    -0.22
     organisé
    -0.21
    åIJij社ä¼ļ
    -0.21
    primitive
    -0.21
    marginTop
    -0.21
    apsulation
    -0.20
    okable
    -0.20
    &);↵↵
    -0.20
     èĩªåĬ¨çĶŁæĪIJ
    -0.20
    POSITIVE LOGITS
     burge
    0.28
    ä¸Ģ个èģĮä¸ļ
    0.25
     (;;)
    0.24
    áIJĪ
    0.24
     overnight
    0.23
    .setRotation
    0.23
     ".";↵
    0.22
     "/");↵
    0.21
     solution
    0.21
     (;;
    0.21
    Activations Density 1.229%

    No Known Activations