© 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. 3099
    Prev
    Next
    INDEX
    Explanations

    sesquiterpene, diterpene, lactone

    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
    hani
    -0.10
    reich
    -0.09
    æĥĬå¥ĩ
    -0.09
    åįĪåIJİ
    -0.09
    ç»ĪçĶŁ
    -0.09
    acles
    -0.09
    çIJ®
    -0.09
    .setHorizontal
    -0.09
    ILD
    -0.09
     dạ
    -0.09
    POSITIVE LOGITS
    稳妥
    0.10
    å°Ĭ
    0.09
    æ³±
    0.08
    æ©IJ
    0.08
    å¨ĵ
    0.08
    ectomy
    0.08
    伸æīĭ
    0.08
    سÙħÙĬ
    0.08
    owed
    0.08
    ube
    0.08
    Activations Density 0.003%

    No Known Activations