© 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. 60803
    Prev
    Next
    INDEX
    Explanations

    expressing opinions or states

    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
    æĬ«
    -0.10
    è§Ħéģ¿
    -0.10
    表æī¬
    -0.09
    èĴĮ
    -0.09
    é¹ħ
    -0.09
    èµŀ
    -0.09
    åIJĦæĸ¹éĿ¢
    -0.09
    Gay
    -0.09
    ç»Ģ
    -0.09
    éģ¿å¼Ģ
    -0.09
    POSITIVE LOGITS
    åı¦æľī
    0.13
    æĢİä¹Ī说
    0.11
    æľªå¿ħ
    0.09
    ä¸įåIJĮæĦı
    0.09
     pes
    0.09
    éĻ¤æѤ
    0.09
    éĽĦ
    0.09
    鬻
    0.08
    伺
    0.08
    idders
    0.08
    Activations Density 0.053%

    No Known Activations