© 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. 47611
    Prev
    Next
    INDEX
    Explanations

    find the index

    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
    NING
    -0.10
    èĴ¯
    -0.10
    åķ¼
    -0.10
    æĪijåıijçİ°
    -0.09
    oration
    -0.09
    æĢ»çļĦæĿ¥è¯´
    -0.09
     surroundings
    -0.09
     окÑĢÑĥжа
    -0.09
    ä¸Ģå¼Ģå§ĭ
    -0.09
    .charset
    -0.09
    POSITIVE LOGITS
    åIJĪéĢĤçļĦ
    0.10
    åIJĪéĢĤ
    0.10
    æĽ´å¤ļ精彩
    0.09
    羣缸
    0.09
    è¡ĮæĶ¿å®¡æī¹
    0.08
    å½ĵå¹´
    0.08
    羣å®ŀçļĦ
    0.08
    (s
    0.08
    çķĮéĻIJ
    0.08
    è¶³å¤ŁçļĦ
    0.07
    Activations Density 0.076%

    No Known Activations