© 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. 2086
    Prev
    Next
    INDEX
    Explanations

    }

    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
    åĽĽä¸ªèĩªä¿¡
    -0.29
    éĢīæĭ
    -0.23
    rescia
    -0.22
    monton
    -0.22
    éĩįè¦ģ举æݪ
    -0.21
    ä¸ĢåĽŀäºĭ
    -0.21
    æŁ¥çľĭæĽ´å¤ļ
    -0.21
     pione
    -0.21
     NONINFRINGEMENT
    -0.21
    ç»ıéªĮåĢ¼
    -0.20
    POSITIVE LOGITS
    )↵↵↵↵↵↵↵↵
    0.24
    []{↵
    0.23
    andidate
    0.23
    ogui
    0.23
     âĵĺ
    0.22
    -minus
    0.22
    reation
    0.22
    auce
    0.21
    ****↵
    0.21
    .§
    0.21
    Activations Density 0.197%

    No Known Activations