© 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. 4151
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    ContentLoaded
    -0.25
    sic
    -0.22
    Queryable
    -0.21
    .VisualBasic
    -0.19
     winters
    -0.19
    çĺ¥
    -0.19
     readdir
    -0.19
    osemite
    -0.19
    åľ¨è¿ĩ渡
    -0.19
     ability
    -0.19
    POSITIVE LOGITS
     }}>{
    0.23
    )animated
    0.22
    ió
    0.22
    wiÄĻks
    0.22
    #ga
    0.21
    .'_
    0.21
     (*(
    0.20
    (optional
    0.20
     extrad
    0.20
    [out
    0.20
    Activations Density 0.184%

    No Known Activations