© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2698
    Prev
    Next
    INDEX
    Explanations

    academic and medical fields

    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
    客
    -0.11
    约ä¼ļ
    -0.10
    ksam
    -0.10
    ä¸įç»ı
    -0.09
    çĨ
    -0.09
    éªĬ
    -0.09
    fsp
    -0.09
    anine
    -0.09
    åIJ
    -0.08
     Vog
    -0.08
    POSITIVE LOGITS
    ç®Ģ称
    0.09
     hic
    0.08
    å¥ij
    0.08
     Yan
    0.08
     ÑģÑĩиÑĤ
    0.08
    çıĪ
    0.08
    oj
    0.08
    оÑĩка
    0.07
    æĿĥ
    0.07
    ç§ĥ
    0.07
    Activations Density 0.158%

    No Known Activations