© 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. 349
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    ERRU
    -0.21
    .desktop
    -0.21
    :CGRect
    -0.21
    )./
    -0.20
    errupted
    -0.20
    azers
    -0.20
    atat
    -0.20
    /filepath
    -0.19
    heck
    -0.19
    -finals
    -0.19
    POSITIVE LOGITS
     bergen
    0.23
    RectTransform
    0.22
    .AddDays
    0.21
     RaycastHit
    0.20
     inkl
    0.20
    sole
    0.20
    mares
    0.20
    odd
    0.19
     assistir
    0.19
    主è¦ģä»İäºĭ
    0.19
    Activations Density 0.348%

    No Known Activations