© 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. 3932
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    èħł
    -0.21
    æ¼ıæ°´
    -0.20
     Sharia
    -0.20
    åĨĹ
    -0.19
    opause
    -0.19
     aras
    -0.19
    IJľç´¢
    -0.19
     Pune
    -0.19
     {?>↵
    -0.19
    ander
    -0.19
    POSITIVE LOGITS
    szÄĻ
    0.26
    :frame
    0.23
     Unterstüt
    0.23
    ’B
    0.22
    #ad
    0.22
    Verdana
    0.22
    caffe
    0.22
    usher
    0.22
     *)((
    0.21
    :normal
    0.21
    Activations Density 0.066%

    No Known Activations