© 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. 12356
    Prev
    Next
    INDEX
    Explanations

    additional overhead

    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
    åĭ¤
    -0.09
     Arm
    -0.09
    彪
    -0.09
    ä¸ĢæĹı
    -0.09
    稿件
    -0.09
    åħļæł¡
    -0.09
    æµģåĬ¨æĢ§
    -0.09
     Springs
    -0.09
    èĬĤèĥ½çݯä¿Ŀ
    -0.08
    move
    -0.08
    POSITIVE LOGITS
     overhead
    0.14
    é¢Ŀå¤ĸ
    0.11
    ä¸įåı¯éģ¿åħį
    0.10
     Gibbs
    0.09
    åı¯ä¿¡
    0.09
    夷
    0.09
    åĮħè£ħ
    0.09
    ä½łçŁ¥éģĵ
    0.09
     ÑĥÑģл
    0.09
    åĪ¶çº¦
    0.09
    Activations Density 0.181%

    No Known Activations