© 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. 60877
    Prev
    Next
    INDEX
    Explanations

    cognitive impairment or decline

    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
    éĢ¼
    -0.10
    ç»ĻäºĨæĪij
    -0.10
    ä¸ĢåĪĢ
    -0.09
     gall
    -0.09
    AFF
    -0.09
    è·¨çķĮ
    -0.09
    çģ¶
    -0.08
    æĬĢ
    -0.08
    踢
    -0.08
    æĬ«
    -0.08
    POSITIVE LOGITS
    楼ä¸ĭ
    0.10
    adan
    0.09
    ä¸ĭéĻį
    0.08
    åĿļå®ļä¸į
    0.08
    èĮī
    0.08
    pick
    0.08
     employer
    0.08
    åºļ
    0.08
    _NORMAL
    0.08
     ability
    0.08
    Activations Density 0.091%

    No Known Activations