© 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. 16579
    Prev
    Next
    INDEX
    Explanations

    email inbox organization

    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
    å¨ģ
    -0.09
    üst
    -0.09
    èĥİ
    -0.08
    æııåĨĻ
    -0.08
    被åĬ¨
    -0.08
    æ°¨
    -0.08
    éģ£
    -0.08
     Blogs
    -0.08
    人åĬĽ
    -0.08
    lobals
    -0.08
    POSITIVE LOGITS
    -src
    0.09
    çķ´
    0.09
    åĩºåĩ»
    0.09
    æıIJä¾ĽæĽ´å¤ļ
    0.09
    åĤ»
    0.09
     disappearing
    0.09
    agram
    0.09
    çļĦæĵįä½ľ
    0.09
    ãģĻãģİ
    0.08
    hana
    0.08
    Activations Density 0.260%

    No Known Activations