© 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. 47753
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    ÙħصاÙĦØŃ
    -0.12
    wards
    -0.11
    Ø£ÙĪضاع
    -0.11
    ÙħÙģاÙĪضات
    -0.10
    åģĩåĨĴ
    -0.10
    ÙħصÙĦ
    -0.10
    reh
    -0.10
    استÙģ
    -0.10
    استÙĤÙĦ
    -0.10
    ÙħصÙĦØŃØ©
    -0.10
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯
    0.08
    ä¸ĬçļĦ
    0.08
    lining
    0.08
    便æĺ¯
    0.07
    liga
    0.07
    plat
    0.07
    ODY
    0.07
    åĬ¡
    0.07
    æīįæĺ¯
    0.07
     aut
    0.07
    Activations Density 0.569%

    No Known Activations