© 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. 57714
    Prev
    Next
    INDEX
    Explanations

    endings like 'an', 'ino', 'ad', 'ar', 'ow', 'ica', 'US', 'ery'

    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
    æĺİæĹ¥
    -0.09
    icult
    -0.09
    forth
    -0.09
    å¨ĺå¨ĺ
    -0.08
    åIJĮå¿Ĺ
    -0.08
    iful
    -0.08
    äºĮåŃĹ
    -0.08
    ibilit
    -0.08
    ðŁı¾
    -0.08
    ched
    -0.08
    POSITIVE LOGITS
    æľĢåħ³éĶ®çļĦ
    0.09
    æľĢåħ³éĶ®
    0.09
    ewise
    0.09
    ewith
    0.09
    楽
    0.08
    ereal
    0.08
    æľīèī²éĩijå±ŀ
    0.08
    .shadow
    0.08
    éĿ
    0.08
    ä¸įéĹ´æĸŃ
    0.08
    Activations Density 0.322%

    No Known Activations