© 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. 63933
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or 's

    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
    å§Ĭ妹
    -0.11
    åİĮ
    -0.10
    éĨį
    -0.10
    å¹ķ
    -0.10
     dÆ°
    -0.09
    mare
    -0.09
    برÙĬ
    -0.09
    åħļçļĦé¢Ĩ导
    -0.09
    udson
    -0.09
    çĶ©
    -0.09
    POSITIVE LOGITS
    åıijæĮ¥
    0.10
    ä¸ĵå±ŀ
    0.10
    åIJī祥
    0.09
    Äĩ
    0.09
    è¾Ľèĭ¦
    0.08
    ä¸Ģæĸ¹
    0.08
     lắm
    0.08
    åıijæĮ¥ä½ľçĶ¨
    0.08
     Ish
    0.08
    年代
    0.08
    Activations Density 0.095%

    No Known Activations