© 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. 5991
    Prev
    Next
    INDEX
    Explanations

    Indian place names

    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
     SCE
    -0.11
    stance
    -0.10
    å·´é»İ
    -0.09
    é«ĺå±Ĥ
    -0.09
    (DE
    -0.09
    éľĩ
    -0.08
    زة
    -0.08
    éŨåı£
    -0.08
    VICE
    -0.08
    éŨæĪ·
    -0.08
    POSITIVE LOGITS
    æĺĨå±±
    0.11
     Karnataka
    0.10
    éºĵ
    0.10
    ä¼ģä¸ļåĴĮ
    0.10
    å¼Ī
    0.10
    åĮ£
    0.09
    æ½Ń
    0.09
    èĮķ
    0.09
    å¥ķ
    0.09
    æĮijæĪĺ
    0.08
    Activations Density 0.108%

    No Known Activations