© 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. 60709
    Prev
    Next
    INDEX
    Explanations

    National Register, explorer, Glacier, Book, Fleet

    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
    éĥ¢
    -0.09
    ãĥ¼ãĥĪ
    -0.09
     adipiscing
    -0.09
    éĦ¯
    -0.09
    ä¸Ńå¤ĸ
    -0.09
    agal
    -0.08
    ctest
    -0.08
    emet
    -0.08
    íĻ
    -0.08
     Bek
    -0.08
    POSITIVE LOGITS
    ä¸ĩéĩĮ
    0.11
    娥
    0.09
    åį°è±¡æ·±åĪ»
    0.09
     доÑģÑĤ
    0.08
    åİĨåı²æĢ§
    0.08
    çİŁ
    0.08
    chy
    0.08
    èģĨ
    0.08
    çĿ«
    0.08
    æ¸ł
    0.08
    Activations Density 0.005%

    No Known Activations