© 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. 27724
    Prev
    Next
    INDEX
    Explanations

    possessive 's or "its followed by noun

    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
     excess
    -0.10
     ÑĨел
    -0.09
    触
    -0.08
    è¦ģçĤ¹
    -0.08
    æĽ¿
    -0.08
    å¯Ĩ
    -0.08
    ESCO
    -0.08
    æľĢå¿«
    -0.08
    滥
    -0.08
    olds
    -0.08
    POSITIVE LOGITS
    ä¸İåħ¶
    0.11
    åį´ä¸į
    0.10
    æıĸ
    0.10
    åIJ¸å¼ķæĽ´å¤ļ
    0.10
    çļĦå®ŀåĬĽ
    0.10
    èĴ
    0.09
    å±ģèĤ¡
    0.09
    åºĶæľīçļĦ
    0.09
    åį»
    0.09
    å¼Ģçİ©ç¬ij
    0.09
    Activations Density 0.076%

    No Known Activations