© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4283
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    Negative Logits
    -Owned
    -0.23
    antis
    -0.22
    xDE
    -0.21
    ighbor
    -0.21
    âĸ¹
    -0.20
     Sexo
    -0.20
     typealias
    -0.20
    [Test
    -0.20
     gezocht
    -0.20
     salarié
    -0.19
    POSITIVE LOGITS
    abcdefgh
    0.23
    ÄĻk
    0.23
    ï¼ģ",
    0.22
    malı
    0.21
     Acrobat
    0.21
     Moscow
    0.21
    鸾
    0.20
     downtown
    0.19
    suite
    0.18
    abcdefghijkl
    0.18
    Activations Density 0.656%

    No Known Activations