© 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. 23963
    Prev
    Next
    INDEX
    Explanations

    politics

    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
    çĴŀ
    -0.10
    itarian
    -0.10
    CLE
    -0.09
    holm
    -0.09
    ç»Ŀ
    -0.09
    æĥ³ä¸įåĪ°
    -0.09
    åįıä¼ļä¼ļéķ¿
    -0.08
    ضÙĦ
    -0.08
    äºĨ个
    -0.08
    oran
    -0.08
    POSITIVE LOGITS
    alem
    0.11
    pus
    0.10
    æŶæķĪ
    0.09
    è¿Ļä¸ĢçĤ¹
    0.09
    blur
    0.09
    æĸ°å±ĢéĿ¢
    0.09
    ecast
    0.09
    ename
    0.09
    Ñĥй
    0.08
    orman
    0.08
    Activations Density 0.008%

    No Known Activations