© 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. 56476
    Prev
    Next
    INDEX
    Explanations

    Brand offers and promotions

    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
    ç³Ł
    -0.09
    åĩłçĤ¹
    -0.09
    å¼ķèµ·äºĨ
    -0.08
    ç²ķ
    -0.08
    æĪIJåĬŁçļĦ
    -0.08
     Pens
    -0.08
    ç¡ķ
    -0.08
    æĴ¼
    -0.08
    æĢ¥äºİ
    -0.08
    åıŁ
    -0.08
    POSITIVE LOGITS
    ä¸ĵå±ŀ
    0.12
     Celtic
    0.10
    ä¸įä½İäºİ
    0.10
    ä¸ĵ人
    0.09
    èĵĸ
    0.09
    éķ¿è¾¾
    0.09
     Spar
    0.09
     гаÑĢан
    0.09
    ä¸įå°ijäºİ
    0.09
    对ä¼ģä¸ļ
    0.08
    Activations Density 0.062%

    No Known Activations