© 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. 311
    Prev
    Next
    INDEX
    Explanations

    measurement and tests

    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
    relu
    -0.20
     tritur
    -0.20
    çī¹æķĪ
    -0.19
    setScale
    -0.19
    æĬ±ä½ı
    -0.19
    gewater
    -0.19
    filtro
    -0.19
    егоднÑı
    -0.19
    鬻
    -0.19
     caul
    -0.19
    POSITIVE LOGITS
    æµĭéĩı
    0.29
    measure
    0.29
     measuring
    0.27
     conducted
    0.27
     analysis
    0.25
     potrÃł
    0.25
     entreprene
    0.25
     tests
    0.24
     measurement
    0.24
     measurements
    0.23
    Activations Density 3.817%

    No Known Activations