© 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. 1007
    Prev
    Next
    INDEX
    Explanations

    food and recipes

    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
     Cbd
    -0.38
     roma
    -0.31
     carbohydr
    -0.30
     fod
    -0.27
    å·§åħĭ
    -0.25
     @"\
    -0.24
    å·¥ä½ľä½ľé£İ
    -0.24
     اÙĦسادس
    -0.24
     maté
    -0.24
    èĥĨåĽº
    -0.24
    POSITIVE LOGITS
     maneu
    0.36
    /↵↵↵↵
    0.35
     ingredients
    0.25
     varieties
    0.25
     defaultMessage
    0.24
    ç¡ķ士çłĶ究
    0.24
    æľīæľŁå¾Ĵ
    0.24
    iÄĻ
    0.24
    åĵģç§į
    0.23
    }'",
    0.23
    Activations Density 3.946%

    No Known Activations