© 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. 33679
    Prev
    Next
    INDEX
    Explanations

    sales and service

    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
     Beste
    -0.10
     âĢ¦↵↵
    -0.08
    æ¯
    -0.08
     ìĿ´ìķ¼
    -0.08
     ê°Ģìļ´
    -0.08
    åľ¨æѤä¹ĭåīį
    -0.08
    eur
    -0.08
    tek
    -0.08
    çİķ
    -0.08
     ngân
    -0.08
    POSITIVE LOGITS
    å½ĵä¹ĭæĹłæĦ§
    0.09
    ä¹ĭ家
    0.09
    家éķ¿ä»¬
    0.09
    usher
    0.08
    loh
    0.08
    ibal
    0.08
    åIJİæİĴ
    0.08
    ÑĢен
    0.08
    ï¸ı
    0.08
    grunt
    0.08
    Activations Density 1.624%

    No Known Activations