© 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. 12443
    Prev
    Next
    INDEX
    Explanations

    each is

    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
    дей
    -0.10
    æħ§
    -0.09
    两级
    -0.09
    ä¸ĢåĪĩéĥ½
    -0.09
    ะ
    -0.08
    åIJĦé¡¹å·¥ä½ľ
    -0.08
     вÑģего
    -0.08
     ço
    -0.08
    ç§įç§į
    -0.08
    scal
    -0.08
    POSITIVE LOGITS
    éĥ½æľīèĩªå·±
    0.16
    ä¸įåIJĮç¨ĭ度
    0.16
    éĥ½æľī
    0.15
    éĥ½æľīçĿĢ
    0.13
    éĥ½åı¯ä»¥
    0.13
    éĥ½èĥ½
    0.13
    åIJĦæľī
    0.13
    éĥ½ä¼ļæľī
    0.12
     individually
    0.12
    ë§Īëĭ¤
    0.12
    Activations Density 0.214%

    No Known Activations