© 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. 1467
    Prev
    Next
    INDEX
    Explanations

    primary or main

    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
    )./
    -0.27
    agged
    -0.24
    osemite
    -0.23
    Çľ
    -0.22
    AllowAnonymous
    -0.21
    çĸ³
    -0.21
    TexParameter
    -0.21
    /Dk
    -0.20
    )");↵↵
    -0.20
    itizen
    -0.20
    POSITIVE LOGITS
     primary
    0.33
    çªģçł´åı£
    0.32
    åĪĩåħ¥çĤ¹
    0.31
     basis
    0.31
     source
    0.30
    source
    0.29
    çĶ¨æĿ¥
    0.28
     main
    0.27
     PRIMARY
    0.27
    æĿ¥æºIJ
    0.27
    Activations Density 4.147%

    No Known Activations