© 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. 58483
    Prev
    Next
    INDEX
    Explanations

    Hillary Clinton

    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
    穹
    -0.09
    ç¼ĺ
    -0.09
    ahl
    -0.09
    è·³è·ĥ
    -0.08
    çĴĩ
    -0.08
    æĺĻ
    -0.08
    å´Ń
    -0.08
    .lin
    -0.08
    æĭ¼æIJı
    -0.08
    çŀİ
    -0.08
    POSITIVE LOGITS
    å¦ĩ
    0.11
     Hillary
    0.10
    鸡
    0.10
    å²ģæľĪ
    0.10
    Hillary
    0.09
    éĺ´éģĵ
    0.09
    å«Ĥ
    0.09
    èij¬
    0.09
    çļĦæĦıè§ģ
    0.09
    污泥
    0.09
    Activations Density 0.030%

    No Known Activations