© 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. 29769
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    身边çļĦ
    -0.11
    bourne
    -0.10
    ç©¿
    -0.09
    åĬ¨äºº
    -0.09
    æĢ»æĶ¶åħ¥
    -0.09
    æ¯ıä¸Ģ
    -0.09
    èĵģ
    -0.09
     Pier
    -0.09
    artz
    -0.09
    _vi
    -0.08
    POSITIVE LOGITS
    æ¯Ķå¦Ĥ
    0.31
    诸å¦Ĥ
    0.28
    ä¾ĭå¦Ĥ
    0.28
    å¦Ĥ
    0.22
    èѬå¦Ĥ
    0.21
    æ¯Ķå¦Ĥ说
    0.21
     like
    0.19
    ä¾ĭãģĪãģ°
    0.19
     such
    0.18
     seperti
    0.16
    Activations Density 0.300%

    No Known Activations