© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3284
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

    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
     Dems
    -0.21
    acyj
    -0.20
    pio
    -0.20
    igham
    -0.20
    )obj
    -0.20
    éĥ½æľīèĩªå·±
    -0.20
     Jugend
    -0.20
    æĹıèĩªæ²»
    -0.19
    PIO
    -0.19
    벤
    -0.18
    POSITIVE LOGITS
    istringstream
    0.21
    é½IJåħ¨
    0.20
    èį»
    0.18
     bli
    0.18
    趸
    0.17
    /password
    0.17
    ä¸ļ
    0.17
     perv
    0.17
    BootApplication
    0.17
    #pragma
    0.17
    Activations Density 0.048%

    No Known Activations