© 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. 1417
    Prev
    Next
    INDEX
    Explanations

    micro / nano

    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
    ]={↵
    -0.31
    }elseif
    -0.28
    ksam
    -0.28
    ----</
    -0.28
    :System
    -0.26
    )=='
    -0.24
    -BEGIN
    -0.24
    .nlm
    -0.24
    ersed
    -0.24
    VML
    -0.23
    POSITIVE LOGITS
     poil
    0.32
     endors
    0.29
     vidé
    0.25
     Warranty
    0.25
     dikke
    0.25
     hookers
    0.24
     compañero
    0.24
     difficoltÃł
    0.24
     desar
    0.23
     pundits
    0.23
    Activations Density 4.995%

    No Known Activations