© 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. 4298
    Prev
    Next
    INDEX
    Explanations

    structural text markers

    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
    å¾Īå¤ļçݩ家
    -0.23
    inos
    -0.20
    游æĪıæĵįä½ľ
    -0.18
    endoza
    -0.18
    游æĪıéĩĮçļĦ
    -0.18
     long
    -0.18
    åı¤äºº
    -0.18
    æī¼
    -0.18
    DownList
    -0.17
    =:
    -0.17
    POSITIVE LOGITS
    .autoconfigure
    0.23
    ä»Ĭ天å°ıç¼ĸ
    0.21
    ceipt
    0.21
     erotica
    0.21
    ilib
    0.21
    NSData
    0.21
     toItem
    0.20
    AGO
    0.20
     achie
    0.20
    orre
    0.20
    Activations Density 0.001%

    No Known Activations