© 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. 12252
    Prev
    Next
    INDEX
    Explanations

    minority or majority

    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
    æľ¬äºº
    -0.10
    ĥĿ
    -0.09
    滩
    -0.09
    aped
    -0.09
    èĢª
    -0.09
    è°ĥ度
    -0.09
     ×ŀ×ĸ×Ķ
    -0.09
    å°ģ
    -0.09
    ieri
    -0.08
    ç¼Ģ
    -0.08
    POSITIVE LOGITS
     minority
    0.20
    å°ijæķ°
    0.18
     Minority
    0.15
     majority
    0.15
     minorities
    0.15
     Majority
    0.13
    å¤ļæķ°
    0.12
    å°ijæķ°æ°ijæĹı
    0.11
    大å¤ļæķ°äºº
    0.11
    _minor
    0.10
    Activations Density 0.053%

    No Known Activations