© 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. 850
    Prev
    Next
    INDEX
    Explanations

    gene and genetics

    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
    æ¡¢
    -0.24
     initState
    -0.21
     createStackNavigator
    -0.20
    æĿľç»Ŀ
    -0.19
     vbCrLf
    -0.19
    versations
    -0.19
    æ··åIJĪ
    -0.19
     IonicPage
    -0.18
    AllArgsConstructor
    -0.18
    _neurons
    -0.18
    POSITIVE LOGITS
    hores
    0.25
     Ä°ns
    0.25
    家æĹı
    0.25
     ?>"/>↵
    0.25
    æīĢæīĢ
    0.24
     FAMILY
    0.24
    ')."
    0.23
     çĶŁåij½åij¨æľŁ
    0.23
    bsolute
    0.23
    å§Ķå®£ä¼ł
    0.23
    Activations Density 1.881%

    No Known Activations