© 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. 966
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    evity
    -0.21
    .defer
    -0.21
    resden
    -0.20
    åķģ
    -0.20
    abbix
    -0.20
    berapa
    -0.20
    (utf
    -0.20
    rive
    -0.20
     Sexo
    -0.20
    .opensource
    -0.19
    POSITIVE LOGITS
     représ
    0.24
     '.';↵
    0.23
     ".";↵
    0.23
    è¾İ
    0.20
    渡
    0.19
     ApplicationException
    0.19
    èĦ±é¢ĸ
    0.19
     poniew
    0.19
    })();↵↵
    0.18
     avalia
    0.18
    Activations Density 0.925%

    No Known Activations