© 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. 1177
    Prev
    Next
    INDEX
    Explanations

    code and structure

    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
     ($("#
    -0.25
    }}],↵
    -0.22
     èĭ¥è¦ģ
    -0.20
    {/*
    -0.20
    ().'/
    -0.20
     suede
    -0.19
    "}}>↵
    -0.18
    ç»Ĵ
    -0.18
    )__
    -0.18
    eta
    -0.18
    POSITIVE LOGITS
    crast
    0.24
    ÑģÑħод
    0.22
    ihanna
    0.22
    <src
    0.20
    ispens
    0.20
    odon
    0.20
    increments
    0.20
    .EventQueue
    0.20
    )./
    0.20
    prites
    0.20
    Activations Density 0.005%

    No Known Activations