© 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. 16690
    Prev
    Next
    INDEX
    Explanations

    copyright and license statements

    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
    åĪ»
    -0.09
    å¥Ķé©°
    -0.09
    æ½ľ
    -0.09
     Trailer
    -0.09
    åħ¬åijĬ
    -0.08
    Matching
    -0.08
    ä¸Ģ对
    -0.08
    é¢Ĩä¼ļ
    -0.08
    IFT
    -0.08
    æ½ĩæ´Ĵ
    -0.08
    POSITIVE LOGITS
    åİŁåĪĽ
    0.11
     copyright
    0.11
    çīĪæĿĥå½Ĵ
    0.10
     COPYRIGHT
    0.10
    çīĪæĿĥ
    0.10
    å½Ĵå±ŀ
    0.10
    ä¸Ģéĺµ
    0.09
    çīĪæĿĥæīĢæľī
    0.09
    Copyright
    0.09
    ä½ľèĢħæīĢæľī
    0.09
    Activations Density 0.127%

    No Known Activations