© 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. 20917
    Prev
    Next
    INDEX
    Explanations

    past eras and their people

    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
    пÑĥÑģ
    -0.11
    缮åīį为æŃ¢
    -0.10
    çī©ä¸ļåħ¬åı¸
    -0.09
    æĥħåĨµè¿Ľè¡Į
    -0.09
    ä»İåݻ年
    -0.09
    æľĢéĢĤåIJĪ
    -0.09
    tour
    -0.08
    äºĨåĩºæĿ¥
    -0.08
    åĩºèī²
    -0.08
    åħ·ä½ĵæĥħåĨµ
    -0.08
    POSITIVE LOGITS
    å½ĵæŶçļĦ
    0.19
    éĤ£æŶ
    0.16
    éĤ£æŶåĢĻ
    0.16
    éĤ£ä¸ªæŶåĢĻ
    0.14
    å½ĵæŶ
    0.14
    çķ¶æĻĤ
    0.12
     ëĭ¹ìĭľ
    0.12
    ä¸įåĥı
    0.12
     era
    0.11
    æŶ任
    0.11
    Activations Density 0.140%

    No Known Activations