© 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. 4219
    Prev
    Next
    INDEX
    Explanations

    text segments

    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
    uggage
    -0.24
    /Internal
    -0.22
    GuidId
    -0.22
    gnore
    -0.21
    몰
    -0.21
    '],['
    -0.21
    rób
    -0.21
    /Foundation
    -0.20
     ;↵↵↵
    -0.20
    FilterWhere
    -0.20
    POSITIVE LOGITS
    å°±ç»Ļ大家
    0.23
    astically
    0.21
    ãĥĵ
    0.21
    ardi
    0.20
    icago
    0.20
    cairo
    0.20
    è¿¢
    0.19
    宫
    0.19
     signings
    0.18
    foot
    0.18
    Activations Density 0.001%

    No Known Activations