© 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. 721
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    =zeros
    -0.20
    ,ep
    -0.20
    èīı
    -0.20
    ç»
    -0.19
    ãĥ¶æľĪ
    -0.19
    stroy
    -0.19
     jeste
    -0.19
     eskort
    -0.18
     PDT
    -0.18
    ylvania
    -0.18
    POSITIVE LOGITS
    oriously
    0.27
    .FileSystem
    0.23
    ;};↵
    0.22
    \API
    0.22
    å±ŀäºİ
    0.21
    alten
    0.21
     Kapoor
    0.21
    ;');↵
    0.21
    âĪĪ
    0.20
    ','');↵
    0.20
    Activations Density 0.295%

    No Known Activations