© 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. 35032
    Prev
    Next
    INDEX
    Explanations

    Hong Kong, autonomous region

    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
    ç³ł
    -0.10
    è´¿
    -0.10
    å°¾
    -0.10
    è¡Įéķ¿
    -0.09
     grav
    -0.09
    ç´ł
    -0.09
    æ·Ģç²ī
    -0.09
    çIJ¨
    -0.09
    åįİåĮĹ
    -0.08
    ä¸įæŃ»
    -0.08
    POSITIVE LOGITS
    港澳
    0.13
    èĩªæ²»
    0.11
    西èĹı
    0.11
    åľ¨é¦Ļ港
    0.10
    éĢļè¡Įè¯ģ
    0.10
    èĩªæ²»åĮº
    0.10
    çīĽå¥¶
    0.10
    lass
    0.10
    港åĮº
    0.10
    大湾åĮº
    0.10
    Activations Density 0.044%

    No Known Activations