© 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. 2981
    Prev
    Next
    INDEX
    Explanations

    enable javascript

    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
     setBackgroundColor
    -0.20
    ousy
    -0.20
    increments
    -0.19
     hotéis
    -0.19
    çłĿ
    -0.19
    èĬĤ
    -0.18
    ailable
    -0.18
    ema
    -0.18
    icional
    -0.18
    çļĵ
    -0.18
    POSITIVE LOGITS
    (GPIO
    0.25
    æĢª
    0.22
     cunt
    0.21
    æľ¬ç½ij
    0.21
    _firestore
    0.20
     WARRANT
    0.20
    urniture
    0.20
    .SuspendLayout
    0.20
    __,__
    0.19
    missive
    0.18
    Activations Density 0.059%

    No Known Activations