© 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. 3022
    Prev
    Next
    INDEX
    Explanations

    district or neighborhood

    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
    å¥
    -0.10
    åIJİæİĴ
    -0.10
    åĿIJä¸ĭ
    -0.09
    egree
    -0.09
    é«ĺéĢŁåħ¬è·¯
    -0.09
    ä¸ĢæĹı
    -0.09
    妯
    -0.09
    æ²®
    -0.09
    å¢Ļå£ģ
    -0.09
    ëł¹
    -0.09
    POSITIVE LOGITS
    åĮºæĶ¿åºľ
    0.13
    åIJĦåĮº
    0.12
    åĮºåĿĹ
    0.11
     ÑĢайона
    0.10
    çīĩåĮº
    0.10
     neighborhoods
    0.10
    åĮº
    0.10
    åįĢ
    0.10
    åĮºå§Ķ
    0.10
    åĮºåĨħ
    0.10
    Activations Density 0.177%

    No Known Activations