© 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. 4067
    Prev
    Next
    INDEX
    Explanations

    programming 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
    Not in Any Lists

    No Comments

    Negative Logits
    smouth
    -0.24
    NgModule
    -0.23
    TexParameter
    -0.23
    DMETHOD
    -0.21
     nack
    -0.21
    âĹĦ
    -0.21
    .Gray
    -0.20
    æµļ
    -0.20
    ghest
    -0.19
    OrNull
    -0.19
    POSITIVE LOGITS
    spo
    0.21
     ><?
    0.21
    .Singleton
    0.19
    .ToShort
    0.19
     Wend
    0.19
    »
    0.19
    åĢľ
    0.18
    prowad
    0.18
    æĭ¥
    0.18
    (new
    0.18
    Activations Density 0.182%

    No Known Activations