© 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. 4199
    Prev
    Next
    INDEX
    Explanations

    narratives about people

    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
     «
    -0.27
     "
    -0.25
    derabad
    -0.23
    ĥģ
    -0.21
     FindObjectOfType
    -0.21
     ValueEventListener
    -0.20
    èĽĽ
    -0.20
    鸳
    -0.20
     Says
    -0.19
     "(
    -0.19
    POSITIVE LOGITS
    ]|[
    0.23
    ,void
    0.22
     (;;
    0.21
    elsif
    0.21
    彩ç¥ŀ
    0.21
    anson
    0.21
    oklyn
    0.20
    糨
    0.19
    åĪļæīį
    0.19
    areth
    0.19
    Activations Density 0.167%

    No Known Activations