© 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. 6022
    Prev
    Next
    INDEX
    Explanations

    privately held companies

    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
    adge
    -0.10
    èĥĮåıĽ
    -0.09
    éĢļè¯Ŀ
    -0.09
    æ°ijçĶŁ
    -0.09
    Wrapped
    -0.09
    æĿĤ
    -0.09
    _THRESH
    -0.09
    çİ«çij°
    -0.09
    èĢĨ
    -0.09
    å¾Ĺèµ·
    -0.08
    POSITIVE LOGITS
    æĪIJéķ¿
    0.11
    çļĦæĪIJéķ¿
    0.10
    æĪIJéķ·
    0.10
    ä¸Ģæł·çļĦ
    0.09
    çİ°éĺ¶æ®µ
    0.08
    éľ°
    0.08
     Tra
    0.08
    åĽ½å®¶éĩįçĤ¹
    0.08
    æĹºçĽĽ
    0.08
    åĪĽä¼¤
    0.08
    Activations Density 0.047%

    No Known Activations