© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 508
    Prev
    Next
    INDEX
    Explanations

    case

    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
    è¿ĻäºĽä¸ľè¥¿
    -0.25
    bsolute
    -0.23
    createForm
    -0.22
    __,__
    -0.22
    âĮĺ
    -0.21
    resher
    -0.20
     earthqu
    -0.20
    .Comparator
    -0.20
    FOUNDATION
    -0.20
    /avatar
    -0.20
    POSITIVE LOGITS
     case
    0.60
     situations
    0.59
     situation
    0.59
     cases
    0.59
     scenario
    0.58
    æĥħåĨµ
    0.57
    æĥħå½¢
    0.57
    çļĦæĥħåĨµ
    0.55
     scenarios
    0.55
    çļĦæĥħå½¢
    0.54
    Activations Density 2.273%

    No Known Activations