© 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. 4292
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    å¾ĹçĽĬ
    -0.21
     italiani
    -0.20
     Dabei
    -0.19
    uards
    -0.19
     Guzzle
    -0.19
    minecraft
    -0.19
    izzer
    -0.19
    èķ¹
    -0.18
    endereco
    -0.18
    ãħ¤
    -0.18
    POSITIVE LOGITS
    âļĻ
    0.24
    abouts
    0.23
    ERT
    0.22
    ðŁĹ
    0.22
    AMAGE
    0.21
    .HtmlControls
    0.21
    precedented
    0.20
     LoggerFactory
    0.20
    ,eg
    0.19
     ($.
    0.19
    Activations Density 0.004%

    No Known Activations