© 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. 3580
    Prev
    Next
    INDEX
    Explanations

    female pronouns

    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
    çļĦ妻åŃIJ
    -0.37
     himself
    -0.35
    çĪ¶åŃIJ
    -0.31
    娶
    -0.29
    妻åŃIJ
    -0.29
    ãģıãĤĵ
    -0.26
     koji
    -0.26
     stesso
    -0.25
    妻
    -0.24
    ippines
    -0.24
    POSITIVE LOGITS
     herself
    1.12
    她çļĦ
    0.68
     her
    0.65
    åĽłä¸ºå¥¹
    0.54
    ä½Ĩ她
    0.53
    她
    0.52
    å¥¹åľ¨
    0.52
     должна
    0.48
     she
    0.46
     ÙĨÙģسÙĩا
    0.44
    Activations Density 2.051%

    No Known Activations