© 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. 7896
    Prev
    Next
    INDEX
    Explanations

    United Nations and related diplomatic bodies

    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
    Not in Any Lists

    No Comments

    Negative Logits
    sei
    -0.10
    亥
    -0.09
     semi
    -0.09
    ewire
    -0.09
    ldata
    -0.09
    ä¹IJ趣
    -0.08
    ä¸įéĶĻçļĦ
    -0.08
    åľ°å¸¦
    -0.08
    Nation
    -0.08
    _rt
    -0.08
    POSITIVE LOGITS
    ç§ĺ书éķ¿
    0.12
     ÐŃÑĤ
    0.10
    ฯ
    0.09
    å·¥ä½ľèĢħ
    0.09
    سÙģ
    0.08
    lh
    0.08
    lush
    0.08
    lav
    0.08
    CellStyle
    0.08
    æµĬ
    0.08
    Activations Density 0.010%

    No Known Activations