© 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. 26102
    Prev
    Next
    INDEX
    Explanations

    (un-) or (non-) prefixes

    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
    çĶļèĩ³è¿ĺ
    -0.09
    é¢Ŀ头
    -0.09
    é³ŀ
    -0.09
    èĿĮ
    -0.09
    å¤ĸåĽ½äºº
    -0.08
    æĽ´åĥıæĺ¯
    -0.08
    æīĭä¸ĭ
    -0.08
    è°ħ解
    -0.08
    åį¡è½¦
    -0.08
    éģ¿å¼Ģ
    -0.08
    POSITIVE LOGITS
     Rosenstein
    0.10
    LETE
    0.10
    dden
    0.09
    å§ĭ建
    0.09
    ROTO
    0.09
    èī
    0.08
     Gaut
    0.08
    ׼×ij
    0.08
    rette
    0.08
    èĩ³æѤ
    0.08
    Activations Density 0.097%

    No Known Activations