© 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. 40143
    Prev
    Next
    INDEX
    Explanations

    announcement and declaration

    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
    0
    -0.10
    7
    -0.10
    5
    -0.09
    8
    -0.09
    6
    -0.09
    é¢Ĩä¼ļ
    -0.09
    åĨ²
    -0.09
    åĿIJçĿĢ
    -0.09
    9
    -0.09
    3
    -0.08
    POSITIVE LOGITS
    宣å¸ĥ
    0.29
     announcement
    0.21
     announce
    0.21
     announced
    0.19
     announces
    0.19
    åħ¬å¸ĥ
    0.19
    åħ¬åijĬ
    0.18
     announcements
    0.18
    å®ĺ宣
    0.17
    announcement
    0.17
    Activations Density 0.224%

    No Known Activations