© 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. 3035
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities

    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
    lik
    -0.10
    acci
    -0.09
    äºŃ
    -0.08
     pant
    -0.08
    åĽĽæĸ¹
    -0.08
    istr
    -0.08
    emen
    -0.08
     dotyczÄħce
    -0.08
    èĢĮåľ¨
    -0.08
    溢价
    -0.07
    POSITIVE LOGITS
    é«ĺå°Ķ
    0.09
    æļĦ
    0.09
    toi
    0.09
    è¯Ŀ说
    0.09
    ä½łå¥½
    0.09
    nim
    0.09
    azzo
    0.09
    GOP
    0.08
    .GO
    0.08
    migration
    0.08
    Activations Density 1.052%

    No Known Activations