© 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. 823
    Prev
    Next
    INDEX
    Explanations

    titles

    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
     clearColor
    -0.25
     Ipsum
    -0.21
    SystemService
    -0.21
    .CASCADE
    -0.20
    ë³į
    -0.20
    è¸ī
    -0.20
     Gov
    -0.20
    åħ¨å¥Ĺ
    -0.19
    doubleValue
    -0.19
    cuador
    -0.18
    POSITIVE LOGITS
    游æĪı代
    0.29
    游æĪıæĬĢå·§
    0.26
    çļĦ带é¢Ĩ
    0.26
    ãĥµ
    0.25
    *)((
    0.25
    rouw
    0.25
    });↵↵↵↵
    0.24
    }elseif
    0.23
    å±Ĥåĩºä¸į
    0.23
    ÑĦизиÑĩеÑģк
    0.23
    Activations Density 0.530%

    No Known Activations