© 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. 24073
    Prev
    Next
    INDEX
    Explanations

    mountain resort and railway

    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
    à¹ģรà¸ĩ
    -0.09
    èİĺ
    -0.09
    滤
    -0.09
    æĨ§
    -0.09
    å¤ĸ交éĥ¨
    -0.08
     vent
    -0.08
    éļĶéŁ³
    -0.08
    延ç»Ń
    -0.08
    åĬŁè¯¾
    -0.08
    CID
    -0.08
    POSITIVE LOGITS
     elevator
    0.10
    æŀĦæĪIJ
    0.09
    æ´¥
    0.09
     co
    0.09
    欺
    0.09
    çĶµæ¢¯
    0.08
    æ·Į
    0.08
    åķ¼
    0.08
     Loft
    0.08
    ijľ
    0.08
    Activations Density 0.048%

    No Known Activations