© 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. 1691
    Prev
    Next
    INDEX
    Explanations

    numerical comparison

    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
    åľ¨ç½ij绾
    -0.23
    è¯ģåĪ¸æĬķèµĦ
    -0.23
    .squareup
    -0.21
    eyJ
    -0.20
     filmer
    -0.20
    айд
    -0.20
    èĻĵ
    -0.20
    èħŃ
    -0.20
     airstrikes
    -0.20
    åĬŀå®ŀäºĭ
    -0.20
    POSITIVE LOGITS
     tileSize
    0.23
     GÅĤ
    0.23
    printStats
    0.22
    fontWeight
    0.22
    scrição
    0.22
    æıĨ
    0.21
    ornment
    0.21
    iership
    0.21
     Waist
    0.21
    ims
    0.21
    Activations Density 0.082%

    No Known Activations