© 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. 3364
    Prev
    Next
    INDEX
    Explanations

    days of week and time

    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
    bsolute
    -0.20
    anager
    -0.20
     trợ
    -0.20
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.20
     pushViewController
    -0.19
    ä¿Ŀ
    -0.18
    Segue
    -0.18
    ISED
    -0.18
     withStyles
    -0.18
     sve
    -0.18
    POSITIVE LOGITS
    ")));
    0.23
    .xticks
    0.21
    (jq
    0.20
     MainAxisAlignment
    0.20
    ëĥĪ
    0.20
    =\"";↵
    0.20
    :animated
    0.19
    <path
    0.19
    NegativeButton
    0.19
    好åIJĹ
    0.19
    Activations Density 0.094%

    No Known Activations