© 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. 1290
    Prev
    Next
    INDEX
    Explanations

    defined / proven

    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
     various
    -0.24
     acompaña
    -0.24
    çĸ³
    -0.23
    çĸĸ
    -0.23
    Çľ
    -0.23
    -Semit
    -0.22
    .']
    -0.22
    ients
    -0.22
    Çļ
    -0.21
    pollo
    -0.20
    POSITIVE LOGITS
    ly
    0.29
    /original
    0.28
    ely
    0.27
    æĿ¥çľĭçľĭåIJ§
    0.26
    ;y
    0.25
    exampleInputEmail
    0.25
    èĢĮåıĪ
    0.25
    /shared
    0.25
     yet
    0.24
     albeit
    0.24
    Activations Density 4.720%

    No Known Activations