© 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. 4010
    Prev
    Next
    INDEX
    Explanations

    Ethiopia and Ethiopian 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
     pies
    -0.09
    汤
    -0.09
    梢
    -0.09
    ãģĹãģ¾ãģĦ
    -0.09
    çĵľ
    -0.09
    pector
    -0.08
    æĪİ
    -0.08
    pu
    -0.08
    åĨį说
    -0.08
    å´´
    -0.08
    POSITIVE LOGITS
     Ethiopia
    0.09
    æ»ĩ
    0.09
    çł»
    0.09
    èİľ
    0.09
     Ethiopian
    0.09
    害ç¾ŀ
    0.09
     Ethi
    0.09
    åŀ´
    0.09
    é«ĺåİŁ
    0.09
     Highlander
    0.08
    Activations Density 0.041%

    No Known Activations