© 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. 29396
    Prev
    Next
    INDEX
    Explanations

    al-LÄģythi

    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
    ç»Ī
    -0.11
    ä¸įæĿ¥
    -0.09
    Bid
    -0.08
     shadow
    -0.08
    Shadow
    -0.08
     Shadow
    -0.08
     bid
    -0.08
    çļĦæľĢåIJİä¸Ģ
    -0.08
     manifest
    -0.07
    æĺĵ
    -0.07
    POSITIVE LOGITS
    èħ¾é£ŀ
    0.09
     Loft
    0.09
    ç¦Ģ
    0.09
    olla
    0.09
    åIJŀ
    0.09
    åįļè§Ī
    0.09
    /release
    0.08
    åķ¬
    0.08
    åºļ
    0.08
    _modes
    0.08
    Activations Density 0.038%

    No Known Activations