© 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. 47660
    Prev
    Next
    INDEX
    Explanations

    nor or and

    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
    马
    -0.09
    /animate
    -0.09
    馬
    -0.09
    าà¸Ļ
    -0.09
    ivo
    -0.09
    Ùħغرب
    -0.09
    å¹´ä¹ĭ
    -0.09
    KANJI
    -0.09
    ocale
    -0.09
     обоÑĢÑĥд
    -0.09
    POSITIVE LOGITS
    ä¸Ģ份
    0.10
    çļĦæĪIJ绩
    0.10
    çļĦ女人
    0.10
     the
    0.09
    çļĦæ¯į亲
    0.09
    以åıĬ
    0.09
    çļĦåIJĪä½ľ
    0.09
    çļĦä¸Ģéĥ¨åĪĨ
    0.09
    çļĦåĪ©çĽĬ
    0.09
    çļĦ人
    0.09
    Activations Density 0.305%

    No Known Activations