© 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. 33866
    Prev
    Next
    INDEX
    Explanations

    Shanghai and its related places

    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¿İ
    -0.11
    è±³
    -0.09
    ç»ıå¼Ģ
    -0.09
    èį¦
    -0.09
    èĪĽ
    -0.09
    磴
    -0.09
    çľģåĨħ
    -0.09
    æ³ķå®ļ
    -0.09
    èĻ¢
    -0.09
    衲
    -0.09
    POSITIVE LOGITS
    沪
    0.17
    æµ¦ä¸ľ
    0.16
    åľ¨ä¸Ĭæµ·
    0.15
    ä¸Ĭæµ·
    0.13
    ä¸Ĭæµ·å¸Ĥ
    0.12
     Shanghai
    0.11
     Chicago
    0.11
    滩
    0.11
    å¥ī
    0.10
    Chicago
    0.10
    Activations Density 0.016%

    No Known Activations