© 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. 764
    Prev
    Next
    INDEX
    Explanations

    statistical significance

    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
    å¿łå®ŀ
    -0.20
    grily
    -0.19
    (CancellationToken
    -0.19
    ERVED
    -0.19
     tạp
    -0.19
     Towers
    -0.18
    waż
    -0.18
     Alamofire
    -0.18
    CLUDING
    -0.18
     addslashes
    -0.18
    POSITIVE LOGITS
    å·®å¼Ĥ
    0.32
     difference
    0.30
    []>↵
    0.30
     differences
    0.28
    ifference
    0.25
     significance
    0.25
     comparing
    0.25
    difference
    0.25
    )(*
    0.25
     statistically
    0.23
    Activations Density 0.486%

    No Known Activations