© 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. 59462
    Prev
    Next
    INDEX
    Explanations

    medical terms

    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
    enser
    -0.08
    aven
    -0.08
     Ðļа
    -0.08
    æĺİçĻ½äºĨ
    -0.08
    _ENT
    -0.08
    éķĶ
    -0.08
    up
    -0.08
    /english
    -0.08
    four
    -0.07
    äºı
    -0.07
    POSITIVE LOGITS
    ä¹ĭå¤ĸ
    0.11
    ç»Ļä»ĸ们
    0.10
    ä¹ĭä¸Ĭ
    0.10
    åIJİå¤ĩ
    0.10
     otherwise
    0.09
    çļĦåŁºç¡Ģä¸Ĭ
    0.09
    æĹģ
    0.09
    lesh
    0.09
    为åħ¶
    0.09
    以å¤ĸ
    0.09
    Activations Density 0.679%

    No Known Activations