© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2792
    Prev
    Next
    INDEX
    Explanations

    masks

    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
    ilmington
    -0.30
    ".↵↵↵↵
    -0.25
    stants
    -0.24
    byss
    -0.24
    BarItem
    -0.23
    eselect
    -0.23
    jej
    -0.23
    -Sep
    -0.23
    roscope
    -0.23
    /XMLSchema
    -0.22
    POSITIVE LOGITS
     mask
    0.28
     masks
    0.27
     throat
    0.27
     face
    0.24
    mask
    0.23
     forehead
    0.22
    é¼»
    0.22
     nasal
    0.22
    éĿ¢åħ·
    0.22
     Mask
    0.21
    Activations Density 0.247%

    No Known Activations