© 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. 1
    Prev
    Next
    INDEX
    Explanations

    O or Op

    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
     ElseIf
    -0.21
    elsif
    -0.21
    ynamo
    -0.20
    æĹ»
    -0.20
    头
    -0.20
     promin
    -0.20
    GY
    -0.20
    olest
    -0.18
     Essen
    -0.18
    éłŃ
    -0.18
    POSITIVE LOGITS
    游æĪıæĬĢå·§
    0.26
    建档ç«ĭ
    0.22
    .scalablytyped
    0.22
    ilmington
    0.21
    ivre
    0.21
     Siri
    0.21
    ppo
    0.20
    Èĺ
    0.20
    |unique
    0.20
    èħļ
    0.20
    Activations Density 0.001%

    No Known Activations