© 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. 58074
    Prev
    Next
    INDEX
    Explanations

    intended for

    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
    èī
    -0.09
    èĮ¬
    -0.09
    æł·åŃIJ
    -0.09
    åı¯èĥ½æĢ§
    -0.09
    æĦıåĽ¾
    -0.09
    åı¯ä»¥æĽ´å¥½
    -0.08
     возмож
    -0.08
    çĤ¹äºĨ
    -0.08
     обÑıзаÑĤелÑĮно
    -0.08
     ::
    -0.08
    POSITIVE LOGITS
    éĤ£äºĽ
    0.11
    ä»»ä½ķå½¢å¼ı
    0.11
    око
    0.10
    ä»»ä½ķ人
    0.10
    à¸Ļำà¹Ħà¸Ľ
    0.10
    è°ĥåĬ¨
    0.10
    ä»»ä½ķ
    0.09
    é¢ī
    0.09
    amon
    0.09
    ä»»ä½ķä¸Ģ个
    0.09
    Activations Density 0.066%

    No Known Activations