© 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. 16673
    Prev
    Next
    INDEX
    Explanations

    Ecuador, Coast, Oregon, River

    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
    çĽijçĿ£ç®¡çIJĨ
    -0.10
    pire
    -0.10
    çŃļ
    -0.09
    /tutorial
    -0.09
     знак
    -0.09
    å¶Ĥ
    -0.09
    .biz
    -0.09
    èĥ¸åīį
    -0.08
     Rutgers
    -0.08
    褶
    -0.08
    POSITIVE LOGITS
    西å®ģ
    0.09
    èĴĻ
    0.09
    纲
    0.09
    èĨı
    0.09
    çģµ
    0.09
     Horde
    0.08
    对åѦçĶŁ
    0.08
    æĹ¥æĬ¥è®°èĢħ
    0.08
    æľī两ç§į
    0.08
    DOI
    0.08
    Activations Density 0.078%

    No Known Activations