© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35971
    Prev
    Next
    INDEX
    Explanations

    Switzerland and Swiss cities

    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
    å¼ºåĽ½
    -0.09
    æ±´
    -0.08
    à¸Ľà¸²à¸ģ
    -0.08
    åŁĥåıĬ
    -0.08
    æ±Łè¥¿
    -0.08
    åĴ¸
    -0.08
    å©Ĭ
    -0.08
    amazon
    -0.08
    .Concat
    -0.08
    elson
    -0.08
    POSITIVE LOGITS
    çijŀ士
    0.20
     Swiss
    0.19
     Switzerland
    0.18
     Zurich
    0.17
    æĹ¥åĨħ
    0.13
     Geneva
    0.12
     Basel
    0.12
    éĵİ
    0.11
    åıijå±ķ空éĹ´
    0.10
    éļĨ
    0.10
    Activations Density 0.158%

    No Known Activations