© 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. 844
    Prev
    Next
    INDEX
    Explanations

    technical terms and names

    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
    éĵŁ
    -0.29
    'url
    -0.25
    'icon
    -0.24
    éĴĮ
    -0.23
    ä»ĵä½į
    -0.23
    éĵĮ
    -0.23
    éĶĨ
    -0.22
    поÑĩÑĤ
    -0.21
     desar
    -0.21
    peater
    -0.21
    POSITIVE LOGITS
    âļĹ
    0.31
    ðŁĵIJ
    0.27
     menn
    0.26
     jihadists
    0.26
    REAK
    0.26
    ilmington
    0.26
    女æĢ§æľĭåıĭ
    0.26
    ãĤĤãģ¡ãĤį
    0.26
     filmer
    0.26
     prive
    0.26
    Activations Density 7.871%

    No Known Activations