© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1477
    Prev
    Next
    INDEX
    Explanations

    Premier League

    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
    تضÙħÙĨ
    -0.25
    Türkiye
    -0.25
    .borderWidth
    -0.25
     )↵↵↵↵↵↵↵↵
    -0.24
     goof
    -0.23
     sesso
    -0.23
     Erect
    -0.23
    .cornerRadius
    -0.23
    f
    -0.22
     Overrides
    -0.22
    POSITIVE LOGITS
    verständlich
    0.37
    íĶĦë¡ľê·¸
    0.30
    ,eg
    0.29
    -valu
    0.29
    resultCode
    0.28
     ());↵↵
    0.27
    =====↵
    0.27
     krist
    0.27
     yeti
    0.26
    _refl
    0.26
    Activations Density 12.452%

    No Known Activations