© 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. 49147
    Prev
    Next
    INDEX
    Explanations

    Indo-European, bronze age, genetic structure, mtDNA, travelling

    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»ĭåħ¥
    -0.09
    	Con
    -0.09
    éħµ
    -0.09
    å¾Ĺèµ·
    -0.09
    人工
    -0.09
    ä¸Ģç¢Ĺ
    -0.09
    å¼ĢåĬŀ
    -0.08
    ä¸įåĨį
    -0.08
    ony
    -0.08
     Orb
    -0.08
    POSITIVE LOGITS
    -metadata
    0.09
    è®°å¿ĨåĬĽ
    0.09
     zer
    0.09
     cust
    0.09
    èĦ±
    0.08
    蹬
    0.08
    è´´åIJ§
    0.08
    æijĦ
    0.08
    ê¶ģ
    0.08
    AVOR
    0.08
    Activations Density 0.094%

    No Known Activations