© 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. 12165
    Prev
    Next
    INDEX
    Explanations

    province, state, or region

    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
    ÑĢев
    -0.22
    оÑĩ
    -0.21
    æŃ£æĸĩ
    -0.20
    лом
    -0.19
    ļĮ
    -0.18
    æİĴ
    -0.18
    åģıåIJij
    -0.18
    å°ıåĮº
    -0.18
     dub
    -0.18
    æĥħæĻ¯
    -0.17
    POSITIVE LOGITS
    åľ°åĮº
    0.32
    åľ°åĮºçļĦ
    0.30
    åľ°åįĢ
    0.25
    -region
    0.24
     regions
    0.24
     region
    0.24
    å·ŀ
    0.24
    çľģ份
    0.24
    å·ŀåĮº
    0.23
     Province
    0.23
    Activations Density 0.242%

    No Known Activations