© 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. 973
    Prev
    Next
    INDEX
    Explanations

    code and markup

    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
    ï¼ģ');↵
    -0.24
     honda
    -0.24
    úsqueda
    -0.22
    versations
    -0.21
     ******************************************************************************↵
    -0.20
     intox
    -0.20
    çļĦ带é¢Ĩ
    -0.19
    _ORIENTATION
    -0.19
     mojo
    -0.19
     },{
    -0.19
    POSITIVE LOGITS
    )))),
    0.28
    íĬ¼
    0.27
    cstdint
    0.23
    []=$
    0.23
    gnore
    0.23
    -INF
    0.22
    Äĩe
    0.22
    );?>↵
    0.21
    окÑĥменÑĤ
    0.21
    âĮĪ
    0.21
    Activations Density 0.015%

    No Known Activations