© 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. 631
    Prev
    Next
    INDEX
    Explanations

    hip hop artists and releases

    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
    æ¥Ĥ
    -0.10
    èĪįå¾Ĺ
    -0.09
    ãĥĽãĥ¼ãĥ«
    -0.09
    èĢ¶
    -0.08
    æĵĺ
    -0.08
    æİ¥æīĭ
    -0.08
    裾
    -0.08
     Pixar
    -0.08
    åĺ¤
    -0.08
    ÑĢог
    -0.08
    POSITIVE LOGITS
    鬼
    0.10
     rapper
    0.09
    ç¾İåѦ
    0.09
    éĴŀ
    0.09
     Kanye
    0.09
    /releases
    0.08
    _ghost
    0.08
    izzy
    0.08
     Rap
    0.08
     tape
    0.08
    Activations Density 0.244%

    No Known Activations