© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3146
    Prev
    Next
    INDEX
    Explanations

    viewing messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ç¨ĭ度
    -0.26
    éĢĤ度
    -0.24
    å§ĭç»Ī
    -0.24
    å°ij许
    -0.23
    度è¿ĩ
    -0.23
    åĨį次
    -0.23
    æĽ´å¥½åľ°
    -0.23
    ä»»ä½ķå½¢å¼ı
    -0.23
     Babe
    -0.22
    ä¸įä¸ĭ
    -0.22
    POSITIVE LOGITS
    å°±çŁ¥éģĵ
    0.26
    æľīçĶ¨çļĦ
    0.23
    ibling
    0.22
    ÙħصاÙĦØŃ
    0.22
    ÑĤол
    0.21
    äºĨåIJĹ
    0.21
    å²±
    0.20
     spit
    0.19
    缴èĩ³
    0.19
     deltas
    0.18
    Activations Density 0.048%

    No Known Activations