© 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. 777
    Prev
    Next
    INDEX
    Explanations

    introduction and concepts

    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
    âļĹ
    -0.31
    ðŁĵIJ
    -0.25
    âĢ¦↵↵↵↵
    -0.24
    =Value
    -0.24
    ðŁļ©
    -0.23
    '>".$
    -0.23
    uxtap
    -0.23
    byss
    -0.23
    ðŁĵĻ
    -0.23
    olics
    -0.22
    POSITIVE LOGITS
     reviewer
    0.23
    TimeString
    0.21
    imeType
    0.20
     Afr
    0.19
     EÄŁer
    0.19
    /sweetalert
    0.19
    ç®Ń
    0.19
     $('#'
    0.18
    ior
    0.18
    кÑĥÑĢ
    0.18
    Activations Density 0.001%

    No Known Activations