© 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. 3387
    Prev
    Next
    INDEX
    Explanations

    actual

    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
    'order
    -0.20
    stå
    -0.19
    Aceptar
    -0.19
     MySqlCommand
    -0.19
    haus
    -0.19
     básico
    -0.19
    หมà¸Ķ
    -0.18
    steller
    -0.18
     createStackNavigator
    -0.18
    comed
    -0.18
    POSITIVE LOGITS
    å®ŀéĻħ
    1.05
     actual
    0.95
    çļĦå®ŀéĻħ
    0.89
    actual
    0.85
     Actual
    0.82
    Actual
    0.77
    實éļĽ
    0.69
    _actual
    0.68
    .actual
    0.65
    å®ŁéļĽãģ«
    0.65
    Activations Density 1.137%

    No Known Activations