© 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. 2557
    Prev
    Next
    INDEX
    Explanations

    URLs and web paths

    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
    .jsoup
    -0.22
     )}↵↵
    -0.21
    jej
    -0.20
    "),"
    -0.20
     Datensch
    -0.20
    ...]↵↵
    -0.19
    .userInteractionEnabled
    -0.19
    âĶı
    -0.19
    å¾ħ
    -0.19
    ä¾Ķ
    -0.19
    POSITIVE LOGITS
    .aspx
    0.24
    沨
    0.22
    .html
    0.21
    HITE
    0.20
    Wind
    0.19
    ä¹İ
    0.19
    lider
    0.19
    é¢ĭ
    0.18
    heten
    0.18
    DidAppear
    0.18
    Activations Density 0.085%

    No Known Activations