© 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. 2904
    Prev
    Next
    INDEX
    Explanations

    combining ingredients

    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
     :";↵
    -0.26
    loquent
    -0.23
    ENUM
    -0.22
     burge
    -0.21
    Mbps
    -0.21
     .↵↵↵↵
    -0.21
     USAGE
    -0.20
    ï¼ģï¼ģ↵↵
    -0.20
    DECL
    -0.20
    oji
    -0.19
    POSITIVE LOGITS
    =add
    0.27
    åĬłåħ¥
    0.21
     add
    0.20
    ÑĦÑĤ
    0.20
    {/*
    0.20
    æĬĦ
    0.20
    èĹģ
    0.19
    ä½ŀ
    0.19
    stdexcept
    0.19
    owntown
    0.19
    Activations Density 0.057%

    No Known Activations