© 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. 1413
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    letcher
    -0.24
     ]}↵
    -0.23
     ("<
    -0.20
     haircut
    -0.19
    orious
    -0.19
    ceries
    -0.19
     Homemade
    -0.19
    .Comparator
    -0.18
     aantal
    -0.18
     wxT
    -0.18
    POSITIVE LOGITS
    requete
    0.26
    .byId
    0.22
    å°±ç»Ļ大家
    0.22
    (indexPath
    0.22
    (parseFloat
    0.22
    çļĦ带é¢Ĩ
    0.22
    æ¯Ķå¦Ĥ说
    0.21
    å¦Ĥæŀľçݩ家
    0.21
     TSRMLS
    0.21
    .withOpacity
    0.21
    Activations Density 1.334%

    No Known Activations