© 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. 26049
    Prev
    Next
    INDEX
    Explanations

    last names of people

    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
    è´¿
    -0.12
    çĵľ
    -0.11
    ä¸įä¸ĭ
    -0.10
    èĥ½æĬĬ
    -0.10
    èĿī
    -0.10
    çļĦè´¨éĩı
    -0.08
    åIJµ
    -0.08
    åĿĬ
    -0.08
    寡
    -0.08
    ÑĥÑĩа
    -0.08
    POSITIVE LOGITS
    æŀģé«ĺ
    0.10
    书éĿ¢
    0.10
     Synd
    0.09
    æĦŁåĬ¨
    0.09
    çĵ®
    0.09
    bra
    0.08
    vig
    0.08
    istro
    0.08
    çĶļ
    0.08
    ında
    0.08
    Activations Density 0.016%

    No Known Activations