© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1188
    Prev
    Next
    INDEX
    Explanations

    also

    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
    ]){
    -0.22
    -initialized
    -0.21
    volución
    -0.20
    ;base
    -0.20
     }}>{
    -0.20
    Çļ
    -0.20
    ovenant
    -0.19
    =fopen
    -0.19
    //---------------------------------------------------------------------------↵↵
    -0.19
    ï¼ģ');↵
    -0.19
    POSITIVE LOGITS
     also
    1.13
    also
    1.02
    Also
    0.89
     Also
    0.89
     ALSO
    0.85
     ÑĤакже
    0.83
     también
    0.82
     juga
    0.78
     também
    0.77
     également
    0.77
    Activations Density 5.290%

    No Known Activations