© 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. 12171
    Prev
    Next
    INDEX
    Explanations

    reminds me of

    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
    éĻĮçĶŁäºº
    -0.12
    éĻĮçĶŁ
    -0.11
    rary
    -0.09
    éĴĴ
    -0.09
    纵è§Ĥ
    -0.09
    红éħĴ
    -0.09
    è¯Ŀè¯ŃæĿĥ
    -0.09
    åİĨåı²æĸ°
    -0.09
    /photo
    -0.09
    åĨĻçĿĢ
    -0.09
    POSITIVE LOGITS
    å°ıæŶåĢĻ
    0.10
    èĩ´
    0.09
    ä»Ģä¹Īåij¢
    0.09
    æŁIJä¸Ģ
    0.09
    å¤Ħå¢ĥ
    0.08
    æŁIJ个
    0.08
    ä¸Ģåı¥
    0.08
    ä¸Ģåı¥è¯Ŀ
    0.08
    éĤ£äºĽ
    0.08
     situations
    0.08
    Activations Density 0.012%

    No Known Activations