© 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. 40396
    Prev
    Next
    INDEX
    Explanations

    beach and bathing

    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
    çĽħ
    -0.09
    æĸ¯åŁº
    -0.09
    ç¼Ł
    -0.09
    berg
    -0.09
    æ¢Ĩ
    -0.09
    éĹ°
    -0.09
    饶
    -0.09
    cope
    -0.09
    æĮĩçĿĢ
    -0.09
     ding
    -0.09
    POSITIVE LOGITS
     beaches
    0.10
    海滩
    0.10
     beach
    0.09
    ä¸ľæµ·
    0.09
    æĻĴ
    0.09
    æµ·æ°´
    0.09
     recl
    0.08
    çļĦæľĢä½³
    0.08
    ç¼İ
    0.08
    åģ¥èº«
    0.08
    Activations Density 0.060%

    No Known Activations