© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24175
    Prev
    Next
    INDEX
    Explanations

    spatial prepositions and locations

    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
    Negative Logits
    ä¸ĢæĬĬ
    -0.10
    lah
    -0.10
    æł¸åĩĨ
    -0.09
    转æĬĺ
    -0.09
     Prem
    -0.09
    _BS
    -0.08
    fold
    -0.08
    并åIJij
    -0.08
    azo
    -0.08
     Concord
    -0.08
    POSITIVE LOGITS
    楣
    0.11
    头顶
    0.10
    称åij¼
    0.10
    åİ¢
    0.10
     buá»ĵn
    0.10
     overhead
    0.09
    bars
    0.09
    èĩ¾
    0.09
    æĤ¬
    0.09
    汶å·Ŀ
    0.09
    Activations Density 0.090%

    No Known Activations