© 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. 598
    Prev
    Next
    INDEX
    Explanations

    technical data

    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
     ApplicationException
    -0.26
     gridColumn
    -0.24
     fullfile
    -0.23
    æĢ§å¼º
    -0.20
     GLenum
    -0.20
     SetLastError
    -0.20
    _EQUALS
    -0.20
    )throws
    -0.19
     nbr
    -0.19
    æĢ§çļĦ
    -0.19
    POSITIVE LOGITS
    :'.$
    0.32
    :".$
    0.31
    ispens
    0.27
    ','=',$
    0.24
    neapolis
    0.23
    logan
    0.23
    -Mobile
    0.23
    bsolute
    0.23
    ."&
    0.23
    .'<
    0.23
    Activations Density 0.684%

    No Known Activations