© 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. 47750
    Prev
    Next
    INDEX
    Explanations

    shipping

    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
    Not in Any Lists

    No Comments

    Negative Logits
    好å¥ĩ
    -0.09
    æĻ°
    -0.08
    ä¸Ģäºĭ
    -0.08
    绣
    -0.08
    éĥ½å°Ĩ
    -0.08
    æĮĪ
    -0.08
    æĺ¯è¦ģ
    -0.08
    å°¿
    -0.08
    æĶ¶æĶ¯
    -0.08
    社
    -0.08
    POSITIVE LOGITS
    æĶ»åĬ¿
    0.13
     flattering
    0.12
    æ±Ĥå©ļ
    0.11
    è¿Ĥ
    0.10
    èµŀç¾İ
    0.10
     woo
    0.10
     íijľíĺĦ
    0.10
    æŀķ
    0.10
    夸
    0.10
    表达
    0.10
    Activations Density 0.069%

    No Known Activations