© 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. 16837
    Prev
    Next
    INDEX
    Explanations

    official or formal

    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
    éĻª
    -0.09
     MÃł
    -0.08
    å¤ļåħĥåĮĸ
    -0.08
    RAFT
    -0.08
    ikan
    -0.08
    ext
    -0.08
    éĻªä¼´
    -0.08
    ä¸İä¸ŃåĽ½
    -0.08
    çĪ½
    -0.08
    ยà¸ģ
    -0.08
    POSITIVE LOGITS
    æŃ£å¼ı
    0.22
    æŃ£è§Ħ
    0.18
     formal
    0.17
     formally
    0.15
    åĽºå®ļçļĦ
    0.14
     official
    0.14
     Formal
    0.13
    æĹ¥æŃ£å¼ı
    0.13
    å®ĺæĸ¹
    0.13
     officially
    0.13
    Activations Density 0.224%

    No Known Activations