© 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. 32909
    Prev
    Next
    INDEX
    Explanations

    South Africa

    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
    åºĩ
    -0.10
    åŃij
    -0.10
    éħ¯
    -0.10
    åħ
    -0.09
    fern
    -0.09
    ighbors
    -0.09
    沧å·ŀ
    -0.09
    ä¹Łå¥½
    -0.09
    æıļ
    -0.09
     assignable
    -0.08
    POSITIVE LOGITS
    åįĹéĿŀ
    0.17
     apartheid
    0.12
     Johannesburg
    0.11
     Mandela
    0.10
    åºŁ
    0.09
    -tracking
    0.09
     SOUTH
    0.09
    æĻ·
    0.09
    åĩĨ
    0.09
    åĨĻåŃĹ楼
    0.09
    Activations Density 0.153%

    No Known Activations