© 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. 3288
    Prev
    Next
    INDEX
    Explanations

    concepts and processes

    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
    oldemort
    -0.21
    .IsMatch
    -0.20
    åįĬ个
    -0.20
    äºĨåįĬ天
    -0.20
     (~(
    -0.19
    对æѤ
    -0.19
    å§Ķåī¯ä¹¦è®°
    -0.19
    -BEGIN
    -0.19
    anske
    -0.19
    <main
    -0.19
    POSITIVE LOGITS
    /Dk
    0.27
    Łèĥ½
    0.21
     ))}↵
    0.21
    yectos
    0.21
    )||(
    0.20
    edly
    0.20
     Patio
    0.20
     itself
    0.20
     nackt
    0.19
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.19
    Activations Density 1.662%

    No Known Activations