© 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. 54437
    Prev
    Next
    INDEX
    Explanations

    cities' possessives

    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
    åĽĬ
    -0.11
    èģĮä¸ļçĶŁæ¶¯
    -0.10
    å¿ĥä¸ŃçļĦ
    -0.10
    çī¹éķ¿
    -0.09
    人çĶŁçļĦ
    -0.09
    ç»ĪçĶŁ
    -0.09
    çĶŁæ¶¯
    -0.09
    Nation
    -0.09
    å¿ĥ缮
    -0.09
    roker
    -0.09
    POSITIVE LOGITS
    å¤ľ
    0.10
    ä»Ģä¹Īåľ°æĸ¹
    0.10
    ä¹Łç®Ĺæĺ¯
    0.10
    vod
    0.10
    建çŃijä¸ļ
    0.09
    éĥ½çŁ¥éģĵ
    0.09
     enam
    0.09
     comp
    0.09
    æĢĢæĬ±
    0.09
    两家
    0.09
    Activations Density 0.043%

    No Known Activations