© 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. 289
    Prev
    Next
    INDEX
    Explanations

    study counts

    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
     Millions
    -0.25
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.23
    sole
    -0.21
    ä¸ĭä¸Ģ
    -0.21
    ãİİ
    -0.20
    秽
    -0.19
     Az
    -0.19
    Mill
    -0.19
    åĩłåĪĨ
    -0.19
    ampions
    -0.19
    POSITIVE LOGITS
    个
    0.30
    herits
    0.29
    人次
    0.28
    )=='
    0.27
    ='<?
    0.26
    pcs
    0.26
    çļĦ带é¢Ĩ
    0.26
     total
    0.26
    .ToShort
    0.25
    âĦī
    0.25
    Activations Density 2.531%

    No Known Activations