© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30500
    Prev
    Next
    INDEX
    Explanations

    Chinese restaurants and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ä¸įç®Ĺ
    -0.09
    åĨľçī§
    -0.09
    åĴ½
    -0.09
     Corpus
    -0.09
    èݽ
    -0.08
    æ¦Ľ
    -0.08
    çªĸ
    -0.08
    ÙħØ®
    -0.08
    æŀŀ
    -0.08
    ican
    -0.08
    POSITIVE LOGITS
     Chinese
    0.18
    Chinese
    0.17
     اÙĦصÙĬÙĨ
    0.16
     chinese
    0.16
    æĺ¯ä¸ŃåĽ½
    0.15
    举äºļ
    0.15
     China
    0.14
    对ä¸ŃåĽ½
    0.14
    ä¸ŃåĽ½
    0.13
    ä¸ŃåĽ½æĶ¿åºľ
    0.13
    Activations Density 0.298%

    No Known Activations