© 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. 59203
    Prev
    Next
    INDEX
    Explanations

    genocide, apartheid, crimes, eradicate

    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
    çĸŁ
    -0.10
    å¼
    -0.10
    æ¹¾åĮº
    -0.09
    éħİ
    -0.09
    ssel
    -0.09
    woods
    -0.09
    èģĶè°Ĭ
    -0.09
    è¨
    -0.09
    ãģĵãĤĵ
    -0.09
    \Base
    -0.08
    POSITIVE LOGITS
    Ñĩи
    0.09
    kah
    0.09
     Kapoor
    0.08
    PLEX
    0.08
    ÙĬÙĪÙĨ
    0.08
    LLL
    0.08
    yon
    0.08
    cakes
    0.08
    èĿĩ
    0.08
    ÙĪرÙĬØ©
    0.08
    Activations Density 0.005%

    No Known Activations