© 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. 59285
    Prev
    Next
    INDEX
    Explanations

    choice between options

    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
    纶
    -0.10
    楼主
    -0.09
    ä½ŀ
    -0.09
    å¾Ī满æĦı
    -0.08
    çļĦè¯Ŀè¯Ń
    -0.08
    æŃ¦å£«
    -0.08
    å¿ħå¤ĩ
    -0.08
    ä½ľåĩºäºĨ
    -0.08
    èĬ¦
    -0.08
    erce
    -0.08
    POSITIVE LOGITS
    继ç»Ń
    0.13
    è¦ģä¹Ī
    0.11
     continued
    0.11
    ç¹¼çºĮ
    0.11
    继ç»Ńä¿ĿæĮģ
    0.10
    .SIG
    0.10
    è¾ķ
    0.10
    ign
    0.10
     Continued
    0.10
    çŃīçĿĢ
    0.10
    Activations Density 0.212%

    No Known Activations