© 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. 1530
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    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
    ä¸ī大éĺ¶æ®µ
    -0.28
    á¼Ħ
    -0.27
    á¼Ķ
    -0.27
    çļĦ带é¢Ĩ
    -0.26
    并ä¸įæĺ¯å¾Ī
    -0.25
    iversal
    -0.24
    :CGRect
    -0.23
    nette
    -0.22
     libertin
    -0.21
     neckline
    -0.21
    POSITIVE LOGITS
    ]='\
    0.23
    :"#
    0.23
    innacle
    0.23
    'icon
    0.23
    {}{↵
    0.22
    [ID
    0.22
    'url
    0.21
    []{↵
    0.21
    },{↵
    0.20
    ä¸Ģå¿ĥ
    0.20
    Activations Density 1.430%

    No Known Activations