© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 231
    Prev
    Next
    INDEX
    Explanations

    introductory or section titles

    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
    /↵↵↵↵
    -0.33
    :'.$
    -0.29
    /stretch
    -0.27
    DMETHOD
    -0.27
    :';↵
    -0.26
    ISOString
    -0.26
    :NSLocalizedString
    -0.25
    OUCH
    -0.25
    ,unsigned
    -0.24
     safeg
    -0.24
    POSITIVE LOGITS
     of
    0.27
    :NS
    0.25
     usern
    0.24
    综
    0.23
     queryInterface
    0.22
    >());↵↵
    0.21
     and
    0.21
    .EventQueue
    0.20
    atego
    0.20
    ↵↵
    0.20
    Activations Density 0.727%

    No Known Activations