© 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. 1201
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    ////↵
    -0.30
    ï¼ĥ
    -0.27
    //č↵č↵
    -0.26
    ÙĤضÙĬ
    -0.25
    ï¼¾
    -0.23
    ullets
    -0.23
    entiful
    -0.23
    ï¼¼
    -0.23
    =\"/
    -0.23
     Ä°stanbul
    -0.23
    POSITIVE LOGITS
     Noticed
    0.25
    .bootstrapcdn
    0.25
    opportunitÃł
    0.24
     NSMutableDictionary
    0.21
     Terr
    0.21
    ÙģÙĬدÙĬÙĪ
    0.20
     Unsure
    0.20
    traî
    0.20
    storeId
    0.20
     resultList
    0.20
    Activations Density 1.485%

    No Known Activations