© 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. 2540
    Prev
    Next
    INDEX
    Explanations

    business opportunities

    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
    .withOpacity
    -0.30
     essentially
    -0.27
     basically
    -0.26
    .circular
    -0.25
    éĢĤæŶ
    -0.23
     generally
    -0.23
    вÑĢеменно
    -0.23
    åIJĮæł·
    -0.22
     specifically
    -0.22
     definit
    -0.22
    POSITIVE LOGITS
    æĺ¯ä¸įåı¯èĥ½
    0.26
    å°±å¤Ł
    0.23
    agnar
    0.22
    è¦ģåģļåĪ°
    0.21
    inidad
    0.21
    paralleled
    0.21
    ä¹ĥæĺ¯
    0.20
    uais
    0.20
    :'/
    0.20
    æľīè¿Ļæł·çļĦ
    0.20
    Activations Density 1.915%

    No Known Activations