© 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. 37707
    Prev
    Next
    INDEX
    Explanations

    Africa and related regions

    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
    æļĤæŶ
    -0.09
    éķ¿ä¸īè§Ĵ
    -0.08
    趾
    -0.08
    ãĥ¼ãĤº
    -0.08
    ziel
    -0.08
    (dy
    -0.08
    æļĿ
    -0.08
    ä¸Ģä¸ĭåŃIJ
    -0.08
    Library
    -0.08
    _clone
    -0.08
    POSITIVE LOGITS
    éĿŀæ´²
    0.13
     African
    0.13
    frican
    0.10
     african
    0.10
    ä¸ī项
    0.09
    agos
    0.09
    è¡Įç¨ĭ
    0.09
     Congo
    0.09
     black
    0.09
     Wak
    0.09
    Activations Density 0.163%

    No Known Activations