© 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. 40089
    Prev
    Next
    INDEX
    Explanations

    hospital names

    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
    åªĴä»ĭ
    -0.09
    uments
    -0.08
    æĮij
    -0.08
    gest
    -0.08
    ç»Ħå§Ķä¼ļ
    -0.08
    代åĬŀ
    -0.08
    æijĪ
    -0.08
    .pm
    -0.08
    åĽ½éĻħåľ¨çº¿
    -0.08
    èĮħ
    -0.08
    POSITIVE LOGITS
    人寿
    0.11
    .jackson
    0.10
    CHK
    0.10
    åĮ»æĬ¤
    0.09
    rac
    0.09
    寿
    0.09
    imity
    0.09
    çļĦæĪĺçķ¥
    0.09
    袱
    0.08
    lie
    0.08
    Activations Density 0.147%

    No Known Activations