© 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. 1193
    Prev
    Next
    INDEX
    Explanations

    results

    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
     unmist
    -0.29
    SenderId
    -0.28
     enthus
    -0.24
    acente
    -0.23
    ábado
    -0.23
    áIJĪ
    -0.23
    SuccessListener
    -0.23
    Slf
    -0.23
     Interracial
    -0.23
    á»ĩnh
    -0.23
    POSITIVE LOGITS
    ç»ĵæŀľ
    0.36
    /results
    0.32
    丰ç¡ķ
    0.31
     result
    0.30
    /result
    0.29
    çµIJæŀľ
    0.28
     results
    0.28
    çļĦç»ĵæŀľ
    0.28
     outcome
    0.26
    .result
    0.26
    Activations Density 3.521%

    No Known Activations