© 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. 60901
    Prev
    Next
    INDEX
    Explanations

    scottish people or places

    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
    æīĢåľ¨åľ°
    -0.10
    èĮ§
    -0.10
    æīĢåľ¨çļĦ
    -0.09
    寰
    -0.08
    ange
    -0.08
    iliar
    -0.08
    满
    -0.08
    é«Ģ
    -0.08
    驹
    -0.07
    åѱ
    -0.07
    POSITIVE LOGITS
    HEME
    0.10
    виÑĤ
    0.10
    人å¿ĥ
    0.09
    HEMA
    0.09
     ÑģлÑĥÑĩа
    0.09
    人æĢ§
    0.09
    -born
    0.09
    /world
    0.09
    æľīèĩªå·±çļĦ
    0.09
     Premiership
    0.09
    Activations Density 0.018%

    No Known Activations