© 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. 2630
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
    檩
    -0.23
    .Parcel
    -0.23
     translateY
    -0.23
    дÑĥмаÑĤÑĮ
    -0.22
     (){
    -0.22
    gne
    -0.21
    驾é©Ń
    -0.21
    åĨħ马
    -0.21
    .nextElement
    -0.21
     Ook
    -0.21
    POSITIVE LOGITS
    antha
    0.22
    arious
    0.21
    ilton
    0.20
    åķľ
    0.20
    decess
    0.19
    )view
    0.19
    örper
    0.19
    Detalle
    0.19
     Sed
    0.19
    }];↵
    0.18
    Activations Density 0.001%

    No Known Activations