© 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. 47533
    Prev
    Next
    INDEX
    Explanations

    turn on or off

    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
    æŀģ大çļĦ
    -0.10
    æ¶İ
    -0.09
    æѤ类
    -0.09
     пи
    -0.08
    HELL
    -0.08
    ä¸Ģå¹ķ
    -0.08
    è¶ħåĩº
    -0.08
    欢ä¹IJ
    -0.08
    ç¼¥
    -0.08
    usch
    -0.08
    POSITIVE LOGITS
    åĵªè£¡
    0.11
    åĵªéĩĮ
    0.09
    éĤ£éĩĮ
    0.09
    æĸ°æīĭ
    0.09
    éĤ£æĺ¯
    0.08
    彩票
    0.08
    æĪijåľ¨
    0.08
    ç©©
    0.08
    èĸªæ°´
    0.08
    áºŃ
    0.08
    Activations Density 0.032%

    No Known Activations