© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1790
    Prev
    Next
    INDEX
    Explanations

    technical or scientific subjects

    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
     porr
    -0.31
     bigot
    -0.30
     siti
    -0.29
     culo
    -0.28
     metic
    -0.28
     desi
    -0.28
     libertine
    -0.28
    -ves
    -0.28
     buc
    -0.26
     namoro
    -0.25
    POSITIVE LOGITS
     oko
    0.28
     nale
    0.26
    InView
    0.25
    rippling
    0.25
    并ä¸įæĺ¯å¾Ī
    0.25
    å¾Īå¤ļçݩ家
    0.25
    traî
    0.25
    ç½ijç«Ļé¦ĸ页
    0.24
    ç½ijç«Ļåľ°åĽ¾
    0.24
    åľ¨çݩ家
    0.24
    Activations Density 17.445%

    No Known Activations