© 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. 1329
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

    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
    ç»Ħç»ĩé¢Ĩ导
    -0.11
    èĭ£
    -0.10
    å¼ĢåıijåĪ©çĶ¨
    -0.10
    åĮĸèĤ¥
    -0.10
    é£Ĵ
    -0.09
    ç¥
    -0.09
    ç´§ç´§åĽ´ç»ķ
    -0.09
    渤
    -0.09
    è®·
    -0.09
    书记
    -0.09
    POSITIVE LOGITS
    åľ¨é¦Ļ港
    0.17
    é¦Ļ港
    0.16
     Hong
    0.14
    HK
    0.13
     HK
    0.12
    粤
    0.11
     Wong
    0.11
    Hong
    0.11
    大湾åĮº
    0.11
    港澳
    0.11
    Activations Density 0.101%

    No Known Activations