© 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. 60925
    Prev
    Next
    INDEX
    Explanations

    no problem with

    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
    å¾Īéĩįè¦ģçļĦ
    -0.11
    æľĢæľī
    -0.10
    	TokenName
    -0.09
    inez
    -0.09
    зад
    -0.09
    æľīçļĦ人
    -0.09
    ê¶ģ
    -0.09
    åĪ®
    -0.09
    ürü
    -0.09
    ivre
    -0.08
    POSITIVE LOGITS
     prefetch
    0.09
    owitz
    0.08
    èĩ
    0.08
    åľ¨èģĮ
    0.08
    eland
    0.08
     whatsoever
    0.08
    .bi
    0.08
    天涯
    0.08
    æ·ĭ
    0.08
    å°Ĩèĩªå·±çļĦ
    0.08
    Activations Density 0.014%

    No Known Activations