© 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. 47422
    Prev
    Next
    INDEX
    Explanations

    contains words describing contents

    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
    ÑĢин
    -0.11
    客æĪ·æıIJä¾Ľ
    -0.10
    æĵį
    -0.10
    ãģĭãĤĭ
    -0.10
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.10
    era
    -0.09
    嫱
    -0.09
    аÑħ
    -0.09
    shots
    -0.09
    chalk
    -0.09
    POSITIVE LOGITS
     Äijá»±ng
    0.15
    çļĦä¸ĢåĪĩ
    0.13
    äºĨ大éĩıçļĦ
    0.11
    forth
    0.10
    æĽ´å¤ļä¿¡æģ¯
    0.10
    丰å¯ĮçļĦ
    0.10
    ively
    0.10
    ãģĻãģ¹ãģ¦
    0.09
    çļĦä¸ĢäºĽ
    0.09
    è¶³å¤ŁçļĦ
    0.09
    Activations Density 0.080%

    No Known Activations