© 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. 6181
    Prev
    Next
    INDEX
    Explanations

    vibration and bouncing

    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
    ä¸Ģçľ¼
    -0.09
    éķĶ
    -0.09
    ofil
    -0.09
    å¤ĩçĶ¨
    -0.09
    èĥ¥
    -0.08
    æĭ¢
    -0.08
     phantom
    -0.08
    伸åĩº
    -0.08
    æĢĻ
    -0.08
     Wend
    -0.08
    POSITIVE LOGITS
     ride
    0.10
    ä¹ĺåĿIJ
    0.10
    éªĢ
    0.09
    å´İ
    0.09
    tre
    0.09
    CADE
    0.09
    äºĶæĺŁ
    0.09
    è¾ĥå·®
    0.09
    ä¸į失
    0.09
    ç³Łç³ķ
    0.09
    Activations Density 0.072%

    No Known Activations