© 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. 62969
    Prev
    Next
    INDEX
    Explanations

    Swiss place names

    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
    å¾Ĺ天
    -0.10
    æĮ¯ãĤĬ
    -0.09
    éĥĵ
    -0.09
    æĺ¯éŁ©åĽ½
    -0.09
    ham
    -0.09
    å±±ä¸ľçľģ
    -0.09
    大åºĨ
    -0.09
    çļĩ家
    -0.08
    åºĦ
    -0.08
    å¥İ
    -0.08
    POSITIVE LOGITS
     Swiss
    0.17
    çijŀ士
    0.16
     Switzerland
    0.16
     Zurich
    0.16
     Geneva
    0.13
    Denver
    0.12
     Denver
    0.10
    çīº
    0.10
    æĹ¥åĨħ
    0.10
    æ¾ľ
    0.10
    Activations Density 0.103%

    No Known Activations