© 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. 52798
    Prev
    Next
    INDEX
    Explanations

    trademarks and copyrights

    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
    éħī
    -0.09
    åĮºåĪ«
    -0.09
    çłĶ究表æĺİ
    -0.09
    èĽ®
    -0.09
    à¹ģà¸ľ
    -0.09
    æ¶Ĥ
    -0.09
    .shtml
    -0.09
    intel
    -0.08
     Stap
    -0.08
    appearance
    -0.08
    POSITIVE LOGITS
    å¯Ĥå¯ŀ
    0.09
    éķ¿éķ¿
    0.08
    è·ĭ
    0.08
    ä¿Ŀå®Ī
    0.08
    fer
    0.08
    ä¹ĸä¹ĸ
    0.08
    caff
    0.08
    calar
    0.08
    bose
    0.08
    çļĦ带é¢Ĩ
    0.08
    Activations Density 0.004%

    No Known Activations