© 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. 3639
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    opsy
    -0.20
    å¶Ļ
    -0.19
    $__
    -0.19
    ÑĤвоÑĢ
    -0.18
    æĺ¯ä¸Ģéĥ¨
    -0.18
     /\.(
    -0.18
    .EventSystems
    -0.17
    ÙħÙĪاÙģÙĤØ©
    -0.17
    æĦ¤æĢĴ
    -0.17
    eden
    -0.17
    POSITIVE LOGITS
     (;;
    0.25
    .erb
    0.21
    .orig
    0.21
    efeller
    0.21
    ,},↵
    0.21
    (ViewGroup
    0.20
    ALSE
    0.20
    -With
    0.20
     (;;)
    0.20
    __);
    0.20
    Activations Density 0.172%

    No Known Activations