© 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. 47662
    Prev
    Next
    INDEX
    Explanations

    being + past participle

    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
    èĥ½å¾ĹåĪ°
    -0.09
    иÑĩеÑģки
    -0.09
    åĪ¶æŃ¢
    -0.08
    ural
    -0.08
    åij½ä¸Ń
    -0.08
    isans
    -0.08
    tingham
    -0.08
    å°ĨæĿ¥
    -0.07
    one
    -0.07
    sound
    -0.07
    POSITIVE LOGITS
    nant
    0.10
    çĥŃè®®
    0.10
    åģļçļĦäºĭ
    0.10
    è¿Ļæł·åģļ
    0.10
    èĥį
    0.09
    ä¸ĸçķĮåIJĦåĽ½
    0.09
    åĬłä¹ĭ
    0.09
    çĶŁæ´»ä¹łæĥ¯
    0.09
     Dess
    0.09
    pur
    0.09
    Activations Density 0.039%

    No Known Activations