© 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. 6552
    Prev
    Next
    INDEX
    Explanations

    geographical location

    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
    æīĢåľ¨çļĦ
    -0.11
    æľ¬ç½ij
    -0.10
    央ä¼ģ
    -0.10
    æīĵäºĨ
    -0.10
    éĴĬ
    -0.10
    mania
    -0.10
    æĿª
    -0.09
    ç»
    -0.09
    åĪĽä¸ļèĢħ
    -0.09
    æľ¬ç¶²ç«Ļ
    -0.09
    POSITIVE LOGITS
    æģ¬
    0.09
    贯彻
    0.09
    快讯
    0.08
     pav
    0.08
    åĬŀåħ¬å®¤
    0.08
     кваÑĢÑĤиÑĢ
    0.08
    åģļ强
    0.08
    _mime
    0.08
     Mime
    0.08
    åıĪ好
    0.08
    Activations Density 0.387%

    No Known Activations