© 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. 4285
    Prev
    Next
    INDEX
    Explanations

    control flow

    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
    ç»Ħç»ĩçĶŁæ´»
    -0.22
     gameTime
    -0.21
     useParams
    -0.20
    åIJĸ
    -0.20
    ]]];↵
    -0.20
    .ERR
    -0.20
     pronto
    -0.20
    quÃŃ
    -0.19
    meye
    -0.19
    åĬ¨çĶŁæĪIJ
    -0.19
    POSITIVE LOGITS
     Dungeons
    0.22
    forgettable
    0.22
    Ymd
    0.21
    çĹķ
    0.20
     #=>
    0.20
    èIJ¥
    0.20
    illions
    0.20
    ahas
    0.20
    puty
    0.19
     _,
    0.19
    Activations Density 0.014%

    No Known Activations