© 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. 1195
    Prev
    Next
    INDEX
    Explanations

    over

    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
    檩
    -0.23
    significant
    -0.23
    precedented
    -0.22
    CLUDED
    -0.22
    зван
    -0.22
    libft
    -0.21
     MediaTek
    -0.21
     CreateMap
    -0.21
    opport
    -0.21
    Roy
    -0.20
    POSITIVE LOGITS
    tones
    0.34
    //"
    0.28
    whelming
    0.27
    //↵↵↵
    0.27
    peater
    0.26
    /**↵↵
    0.26
    ordova
    0.26
    piler
    0.25
    resden
    0.25
    *)_
    0.25
    Activations Density 1.349%

    No Known Activations