© 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. 17546
    Prev
    Next
    INDEX
    Explanations

    Africa and Nigeria

    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»ij
    -0.11
    æī¬å·ŀ
    -0.09
     Gree
    -0.09
    åĨ¬å¤©
    -0.08
    大çIJĨ
    -0.08
    温å·ŀ
    -0.08
     Persian
    -0.08
    æĵ¦
    -0.08
    oria
    -0.08
    vr
    -0.08
    POSITIVE LOGITS
    éĿŀæ´²
    0.21
    Africa
    0.17
     African
    0.15
    åįĹéĿŀ
    0.15
     Africa
    0.15
     Afr
    0.15
     afr
    0.14
     Nigeria
    0.14
     Africans
    0.14
     nigeria
    0.13
    Activations Density 0.539%

    No Known Activations