© 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. 7860
    Prev
    Next
    INDEX
    Explanations

    entertainment and interactive technology 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
    è¾ĺ
    -0.09
    ç©¿è¡£
    -0.09
    gresql
    -0.09
    ä»ij
    -0.09
    éĩijèŀįåį±æľº
    -0.09
    tera
    -0.09
    esome
    -0.09
    ters
    -0.09
    æĿµ
    -0.09
    ä¸įç»ı
    -0.09
    POSITIVE LOGITS
    .acc
    0.10
    çļĦçłĶ究
    0.09
    ç´ł
    0.09
    ä¸Ģå¥Ĺ
    0.08
    ä¸ĵéŨ
    0.08
    åij½
    0.08
    对人ä½ĵ
    0.08
    å°ļ书
    0.08
    çłļ
    0.08
    çIJĨæĥ³çļĦ
    0.08
    Activations Density 0.034%

    No Known Activations