© 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. 2053
    Prev
    Next
    INDEX
    Explanations

    Names starting with O

    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
    æĥ¨
    -0.21
    imb
    -0.20
    /category
    -0.20
    åijĸ
    -0.20
    ä¼ļä¼ļéķ¿
    -0.19
    iffany
    -0.19
    :"-"`↵
    -0.19
    glÄħd
    -0.18
    (IService
    -0.18
    :CGRect
    -0.18
    POSITIVE LOGITS
    redd
    0.21
     pud
    0.20
     }}">
    0.20
    ApiController
    0.20
    Ĵ
    0.20
    urance
    0.19
     strerror
    0.18
    LECT
    0.18
    ople
    0.18
    FXML
    0.18
    Activations Density 0.002%

    No Known Activations