© 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. 1096
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    ï¼ĩ
    -0.27
    Ẽ
    -0.25
    ')."
    -0.24
    scrição
    -0.23
    .'<
    -0.21
    :host
    -0.21
    filer
    -0.21
     LENG
    -0.21
     <+
    -0.21
    ,Th
    -0.20
    POSITIVE LOGITS
    æľīåºı
    0.20
     GameController
    0.20
    accès
    0.20
     createDate
    0.19
     ámbito
    0.19
    并éĢļè¿ĩ
    0.18
     ÙĬÙĪس
    0.18
    ackbar
    0.18
    çļĦç²¾ç¥ŀ
    0.17
     createdBy
    0.17
    Activations Density 0.001%

    No Known Activations