© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3686
    Prev
    Next
    INDEX
    Explanations

    and

    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
     ogóle
    -0.23
    Reducers
    -0.21
    ä¸Ģ身
    -0.19
    æī
    -0.19
     bloginfo
    -0.19
    çļĦç¨ĭ度
    -0.19
    koneksi
    -0.19
    æĪIJ绩åįķ
    -0.18
    bild
    -0.18
    æ·¡æ·¡çļĦ
    -0.18
    POSITIVE LOGITS
    %"><
    0.25
    ?>>
    0.24
    \admin
    0.23
    ($('<
    0.21
    -'.$
    0.20
    acman
    0.20
    icerca
    0.20
    TRIES
    0.20
    uxtap
    0.20
    .yy
    0.19
    Activations Density 0.549%

    No Known Activations