© 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. 47519
    Prev
    Next
    INDEX
    Explanations

    understanding, setting, alteration, doing, failure, knowledge

    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
    çļĦæĸ¹å¼ıæĿ¥
    -0.09
    à¸Ļาà¸Ļ
    -0.09
    èĥľä»»
    -0.09
    .createObject
    -0.09
    åľ¨æĪijçļĦ
    -0.08
    马æĭī
    -0.08
    æĥ³åĪ°äºĨ
    -0.08
    éĻ¢éĻ¢éķ¿
    -0.08
    PCM
    -0.08
    DoubleClick
    -0.08
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.13
    íķĺë©´
    0.12
    è¿Ļæł·çļĦè¯Ŀ
    0.12
    ãģĻãĤĭãģ¨
    0.12
    çļĦè¯Ŀ
    0.11
    èĥ½ä½¿
    0.11
    ä¼ļ使
    0.11
    ëIJĺë©´
    0.10
    ç»Ń
    0.10
    è¿Ļæł·åģļ
    0.10
    Activations Density 0.442%

    No Known Activations