© 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. 1454
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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
    ï¼ģ↵↵↵↵
    -0.28
     beÄŁen
    -0.26
    âĻª↵↵
    -0.25
    >`;↵
    -0.23
     MERCHANTABILITY
    -0.23
     __________________↵↵
    -0.23
    .Disclaimer
    -0.22
    ()=="
    -0.22
     ↵		↵
    -0.22
     desar
    -0.22
    POSITIVE LOGITS
    ↵
    0.57
    ,↵
    0.40
    ↵↵
    0.37
    ;↵
    0.36
    ï¼Į↵
    0.34
    č↵
    0.34
    :↵
    0.34
     ↵
    0.32
    ',↵
    0.30
    ï¼Ľ↵
    0.29
    Activations Density 3.262%

    No Known Activations