© 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. 934
    Prev
    Next
    INDEX
    Explanations

    citations

    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
    nze
    -0.23
    linky
    -0.23
    WRAPPER
    -0.21
    istring
    -0.21
    MAND
    -0.21
     AuthenticationService
    -0.21
     semiclass
    -0.21
     ++)↵
    -0.20
    mtree
    -0.20
    soever
    -0.20
    POSITIVE LOGITS
     lokale
    0.21
    .createFrom
    0.21
     ÙĦدÙĬ
    0.20
    wpdb
    0.19
    åģļ强
    0.19
    æĮºå¥½
    0.18
    .withOpacity
    0.18
    mainwindow
    0.18
    ä»İæł¹æľ¬
    0.17
    å¬Ĺ
    0.17
    Activations Density 0.581%

    No Known Activations