© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8779
    Prev
    Next
    INDEX
    Explanations

    possessive proper nouns

    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¸ī天
    -0.09
    oses
    -0.08
    ä¼Łå¤§
    -0.08
    沦
    -0.08
    eten
    -0.08
    Heroes
    -0.08
    èĢĮè¿Ļ
    -0.08
    æµĥ
    -0.08
    çĪ±æĥħ
    -0.08
    她们
    -0.08
    POSITIVE LOGITS
    çIJĨäºĭ
    0.09
    åŀ
    0.08
    è°·
    0.08
    åĽ¢éķ¿
    0.08
    æĹ¥æ¶Īæģ¯
    0.08
     Mr
    0.08
    alic
    0.08
    è¿ĩéĶĻ
    0.08
     umb
    0.08
    ÙģÙĨ
    0.08
    Activations Density 0.051%

    No Known Activations