© 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. 7677
    Prev
    Next
    INDEX
    Explanations

    dates and numerical sequences

    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
    èį¦
    -0.09
    就没
    -0.09
    æ¯ĶæĪij
    -0.08
    ä¼łéĢģ
    -0.08
    å°±è¿Ļä¹Ī
    -0.08
    å°±æĬĬ
    -0.08
    ä»Ĭ天çļĦ
    -0.08
    ãģ¾ãĤĬ
    -0.08
    æ·¦
    -0.08
     Weekly
    -0.08
    POSITIVE LOGITS
    æľ¬èº«
    0.10
    Ñģад
    0.09
    паÑģ
    0.09
    é¢ĺ主
    0.09
     Copp
    0.09
    Pa
    0.09
    æĵį
    0.08
    ä¿Ĺ
    0.08
    çİ®
    0.08
     Pa
    0.08
    Activations Density 0.136%

    No Known Activations