© 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. 32859
    Prev
    Next
    INDEX
    Explanations

    Republican voters and Democrats

    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
    æ¤į
    -0.09
    æľªç»ı
    -0.08
    ping
    -0.08
    ç¹ģå¿Ļ
    -0.08
    orus
    -0.08
    äºīåĪĽ
    -0.07
    åĮ¿åIJį
    -0.07
    ä¸įæľį
    -0.07
    è°
    -0.07
    çłĶ
    -0.07
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.10
    æļĿ
    0.10
    çļĦæĶ¯æĮģ
    0.09
    ì¢Į
    0.09
    èĶ¼
    0.09
    éĻĮçĶŁ
    0.09
     ì¢
    0.08
    층
    0.08
    IGN
    0.08
    å±ŀäºİèĩªå·±
    0.08
    Activations Density 0.038%

    No Known Activations