© 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. 6268
    Prev
    Next
    INDEX
    Explanations

    street names and highway numbers

    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
    è®¤çľŁåŃ¦ä¹ł
    -0.09
     заÑĢегиÑģÑĤÑĢи
    -0.09
    çĭ¬ä¸ĢæĹłäºĮ
    -0.08
    /generated
    -0.08
    æĬĬæı¡
    -0.08
    iros
    -0.08
    丰å¯Įå¤ļ彩
    -0.08
    秣éĩij
    -0.08
    å¾Ĺ天çĭ¬åİļ
    -0.08
    éģŀ
    -0.08
    POSITIVE LOGITS
    æĶ¹åĸĦ
    0.14
    ä¿®å¤į
    0.10
     lane
    0.09
    åĿij
    0.09
    车éģĵ
    0.09
     lanes
    0.09
    Stretch
    0.09
     капиÑĤ
    0.09
    éĵ£
    0.09
    è¿ĻæĿ¡è·¯
    0.08
    Activations Density 0.082%

    No Known Activations