© 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. 59445
    Prev
    Next
    INDEX
    Explanations

    and much, much more

    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¡å®ŀ
    -0.09
    è¹ļ
    -0.09
    ÑĩÑijÑĤ
    -0.08
    馨
    -0.08
    å®Ľ
    -0.08
    fore
    -0.08
    éĩį
    -0.08
    社ä¼ļç»Ħç»ĩ
    -0.08
    ya
    -0.08
    erer
    -0.08
    POSITIVE LOGITS
    ä¸ĢåIJĮ
    0.10
    èĩ
    0.09
    _IRQn
    0.09
     Nurs
    0.09
    ä¸īä½įä¸Ģä½ĵ
    0.09
    临æŶ
    0.08
    貫
    0.08
    ç¾İçļĦ
    0.08
    ä¿¡æģ¯æľįåĬ¡
    0.08
    eco
    0.08
    Activations Density 0.020%

    No Known Activations