© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33561
    Prev
    Next
    INDEX
    Explanations

    Australian proper nouns and abbreviations

    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
    åĵ½
    -0.08
    çĪ¾
    -0.08
     caffe
    -0.08
    为æѤ
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    çĶľçĶľ
    -0.08
    å¾Īæ·±
    -0.08
    æľīè¿Ļæł·çļĦ
    -0.08
    çĨĺ
    -0.07
    ä¸ŃåĽ½æ±½è½¦
    -0.07
    POSITIVE LOGITS
    ãĥĮ
    0.10
    hes
    0.09
    ãĥĽãĥĨ
    0.09
    edelta
    0.08
    åħĪæĬĬ
    0.08
    IZE
    0.08
    åĽĽå¤§
    0.08
    çķ
    0.08
    å¤ļ彩
    0.08
    izen
    0.08
    Activations Density 0.347%

    No Known Activations