© 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. 54966
    Prev
    Next
    INDEX
    Explanations

    WordPress functions and code

    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
    áºŃn
    -0.11
    çīĮ
    -0.10
    éĦ±
    -0.10
    ળ
    -0.10
    (SYS
    -0.10
    履约
    -0.10
    çĶ«
    -0.10
    ä¸į便
    -0.09
    娱ä¹IJ
    -0.09
    æĹłåģ¿
    -0.09
    POSITIVE LOGITS
     wp
    0.12
    wp
    0.10
     WordPress
    0.10
    WP
    0.10
    	wp
    0.10
    wpdb
    0.10
    (wp
    0.09
    _wp
    0.09
    ç¼ĺ
    0.09
    WordPress
    0.08
    Activations Density 0.272%

    No Known Activations