© 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. 40040
    Prev
    Next
    INDEX
    Explanations

    accused of being a dealer

    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
    uve
    -0.10
    æĺİæľĹ
    -0.09
    enia
    -0.08
    é³ŀ
    -0.08
    osing
    -0.08
    大大å°ıå°ı
    -0.08
    深深
    -0.08
    æµĬ
    -0.08
    umb
    -0.07
    æ®·
    -0.07
    POSITIVE LOGITS
    æĻ®éĢļçļĦ
    0.10
    ä»»ä½ķå½¢å¼ı
    0.10
    常è§Ħ
    0.09
    åIJĮç±»
    0.09
    åĪ«çļĦ
    0.09
    æĭį
    0.09
    æĹłç¼ĺ
    0.09
    带æĿ¥æĽ´å¤ļ
    0.09
    åĥı
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    Activations Density 0.068%

    No Known Activations