© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12658
    Prev
    Next
    INDEX
    Explanations

    American plastic surgery statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    Pager
    -0.20
     vir
    -0.20
    åľ¨å½ĵåľ°
    -0.20
    /gpl
    -0.20
    .geo
    -0.19
    两æīĭ
    -0.19
    éĥİ
    -0.19
    å½ĵåľ°çļĦ
    -0.19
    .qml
    -0.18
    æ¬ł
    -0.18
    POSITIVE LOGITS
    ç¾İåĽ½äºº
    0.24
    Americans
    0.22
    annual
    0.21
    å¹´ä¸ŃåĽ½
    0.21
     American
    0.20
    好çľĭçļĦ
    0.20
    çģ
    0.20
     Trou
    0.20
    static
    0.20
     Hull
    0.19
    Activations Density 0.072%

    No Known Activations