© 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. 64106
    Prev
    Next
    INDEX
    Explanations

    cylindrical shapes and bores

    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
    izedName
    -0.10
    åħ¬çĽĬ
    -0.10
     ÑĩиÑģл
    -0.10
    ç½ij绾ç§ijæĬĢ
    -0.09
    .prevent
    -0.09
    acs
    -0.09
    äºĮ代
    -0.09
    åįĬ天
    -0.09
     обÑĢазом
    -0.09
    å¿Ŀ
    -0.09
    POSITIVE LOGITS
     bü
    0.09
    åĩºç§Ł
    0.08
     ann
    0.08
    .Byte
    0.08
    ä¸Ģç¢Ĺ
    0.08
    å¥Ĺè£ħ
    0.08
    åħ¸
    0.08
    éķ¶
    0.08
    èĻİ
    0.08
    race
    0.08
    Activations Density 0.150%

    No Known Activations