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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1343
    Prev
    Next
    INDEX
    Explanations

    recent or reported

    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
    å¿ĥ仪çļĦ
    -0.23
    "+"
    -0.22
    <main
    -0.21
    "."
    -0.21
    VectorXd
    -0.21
    ropri
    -0.20
    alborg
    -0.20
    roupon
    -0.20
    chos
    -0.20
    )}>
    -0.20
    POSITIVE LOGITS
     recently
    0.36
     recent
    0.31
    recent
    0.30
     reported
    0.28
     reportedly
    0.28
    æľĢè¿ij
    0.27
     studies
    0.27
     [@
    0.25
    Recently
    0.25
     Recently
    0.24
    Activations Density 2.794%

    No Known Activations