© 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. 1901
    Prev
    Next
    INDEX
    Explanations

    children

    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
    éĢĢä¼ij
    -0.28
    èĢģå¹´
    -0.25
    女人
    -0.25
    çĶ·äºº
    -0.25
    好人
    -0.24
     Women
    -0.24
    Women
    -0.24
     WOM
    -0.23
     women
    -0.22
    å¤įå·¥å¤į
    -0.22
    POSITIVE LOGITS
    åģ¥åº·æĪIJéķ¿
    0.44
    åıijèĤ²
    0.36
    æĪIJéķ¿
    0.33
    çļĦæĪIJéķ¿
    0.33
     school
    0.31
    æĶ¾åѦ
    0.30
    æĩĤäºĭ
    0.30
    ä¸ĬåѦ
    0.28
     developmental
    0.28
    æĪIJéķ·
    0.27
    Activations Density 4.930%

    No Known Activations