© 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. 62449
    Prev
    Next
    INDEX
    Explanations

    cultural and religious centers

    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
    å¥ī
    -0.11
    çİ°æľīçļĦ
    -0.10
    è·Łä¸įä¸Ĭ
    -0.10
    ILES
    -0.10
    æĽ´åĥıæĺ¯
    -0.10
    çģ¾éļ¾
    -0.09
    ä¸ĢçĤ¹åĦ¿
    -0.09
    çĶº
    -0.09
    ç´§æī£
    -0.09
    Cors
    -0.09
    POSITIVE LOGITS
    åľ¨éĤ£éĩĮ
    0.13
    åľ¨è¿ĻéĩĮ
    0.12
    è¿ĻéĩĮæĺ¯
    0.11
    æĢ»éĥ¨
    0.11
    åľ¨æѤ
    0.10
    éĹ»åIJį
    0.09
     headquarters
    0.09
    äºİæѤ
    0.09
    dit
    0.09
    åľ¨éĩĮéĿ¢
    0.09
    Activations Density 0.239%

    No Known Activations