© 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. 47587
    Prev
    Next
    INDEX
    Explanations

    great-grand + related terms

    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
    åIJĮä¼´
    -0.10
    æIJŃæ¡£
    -0.10
    ä¼´ä¾£
    -0.09
    å¼Ģå±Ģ
    -0.09
    ä¼Ļä¼´
    -0.09
    åı¦ä¸ĢåįĬ
    -0.08
    ç¼Ļ
    -0.08
    Ļ¶
    -0.08
    ç¼£
    -0.08
    ovsky
    -0.08
    POSITIVE LOGITS
    UDA
    0.10
     grandson
    0.10
    lug
    0.09
    转载
    0.09
    èĩªè´Ł
    0.09
    struments
    0.09
    ç¥ĸçĪ¶
    0.09
    åŃĻåŃIJ
    0.08
    adors
    0.08
     grandfather
    0.08
    Activations Density 0.013%

    No Known Activations