© 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. 60671
    Prev
    Next
    INDEX
    Explanations

    taste of it, feel pressure, feel icy

    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
    biz
    -0.10
    究竣
    -0.10
    樽
    -0.09
     اÙĦØ°
    -0.09
    æīĢæıIJä¾Ľ
    -0.09
    æľĢ大
    -0.09
    åıij表
    -0.09
    被认为æĺ¯
    -0.08
    Ä°R
    -0.08
    è§īå¾Ĺå¾Ī
    -0.08
    POSITIVE LOGITS
    åIJĦçľģ
    0.11
    ses
    0.09
    åħ¨åĽ½åIJĦåľ°
    0.09
    çªŃ
    0.09
    èģĮèĥ½éĥ¨éŨ
    0.09
    ä»ĸ对
    0.09
     tore
    0.08
    é»ı
    0.08
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.08
    åIJĦä½į
    0.08
    Activations Density 0.030%

    No Known Activations