© 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. 2015
    Prev
    Next
    INDEX
    Explanations

    technical code snippets

    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
    -Identifier
    -0.24
    WithContext
    -0.21
    CUS
    -0.21
    herits
    -0.21
    ,");↵
    -0.21
    .Large
    -0.21
    "display
    -0.20
     (;;
    -0.20
    emean
    -0.20
    "user
    -0.20
    POSITIVE LOGITS
    ä¿Ĺ
    0.22
    妾
    0.19
     nost
    0.19
    ë²ħ
    0.19
     shalt
    0.18
    æĭĻ
    0.18
    ยาย
    0.18
    noinspection
    0.18
    _Desc
    0.18
    olk
    0.18
    Activations Density 0.001%

    No Known Activations