© 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. 1473
    Prev
    Next
    INDEX
    Explanations

    programming 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
    Not in Any Lists

    No Comments

    Negative Logits
     длиÑĤелÑĮн
    -0.32
    благо
    -0.30
    владе
    -0.30
     ÑģеÑĢÑĮезн
    -0.30
    ÑģÑĥжден
    -0.29
    :maj
    -0.29
    вÑĢеменно
    -0.29
    плаÑĩива
    -0.28
     положиÑĤелÑĮн
    -0.28
    можем
    -0.28
    POSITIVE LOGITS
     nomine
    0.28
    .OrderByDescending
    0.28
     francaise
    0.28
     mastur
    0.25
     ancor
    0.25
     handleMessage
    0.24
     sperma
    0.24
     desar
    0.23
     Rigidbody
    0.23
     scaleX
    0.23
    Activations Density 0.641%

    No Known Activations