© 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. 14329
    Prev
    Next
    INDEX
    Explanations

    Chinese punctuation and grammar

    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
    ston
    -0.20
    ç»ĵæĻ¶
    -0.18
     packaged
    -0.18
    é¢Ĩè·ij
    -0.17
    éĽªå±±
    -0.17
    fur
    -0.17
    ằ
    -0.17
     wholesale
    -0.17
    ×¢
    -0.16
    æ¾İæ¹ĥ
    -0.16
    POSITIVE LOGITS
    设æĸ½
    0.29
    宽æķŀ
    0.28
    åĨħçļĦ
    0.26
    å¸ĥå±Ģ
    0.25
    çݯå¢ĥ
    0.24
    åĿĢ
    0.24
    åľºæīĢ
    0.24
    éŨåı£
    0.24
    å¸ĥç½®
    0.24
    建设åĴĮ
    0.23
    Activations Density 0.409%

    No Known Activations