© 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. 1222
    Prev
    Next
    INDEX
    Explanations

    descriptive content

    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
    ;');↵
    -0.21
    },'
    -0.20
    ";}
    -0.19
    <Scalar
    -0.19
    西红
    -0.19
    è£ĺ
    -0.19
    ",__
    -0.19
    éta
    -0.19
    )){↵↵
    -0.18
    POSITIVE LOGITS
    iguiente
    0.21
    leanor
    0.21
    emons
    0.20
    DialogContent
    0.20
    并åIJij
    0.19
    aar
    0.19
    æĬ¥ä¸ļ
    0.18
    forgettable
    0.18
     اÙĦÙħج
    0.18
    ç½ijé¦ĸ页
    0.18
    Activations Density 0.002%

    No Known Activations