© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9648
    Prev
    Next
    INDEX
    Explanations

    capitalism, liberalism, profit, class

    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
    éªĹ
    -0.10
    룰
    -0.09
    EIF
    -0.09
    æĽ³
    -0.09
    ìĤ¬íķŃ
    -0.09
    ãĥĬãĥ³
    -0.09
    èĢĮ导èĩ´
    -0.09
    ä¼ļ让
    -0.09
    ç¨İè´¹
    -0.08
    ç½ļ
    -0.08
    POSITIVE LOGITS
    è¿IJä½ľ
    0.09
    .ids
    0.09
    åįģ足
    0.08
    åıĪ好
    0.08
    -leaning
    0.08
    cer
    0.08
    åľ¨ä¸ŃåĽ½
    0.08
    浪潮
    0.08
    ids
    0.08
     pods
    0.08
    Activations Density 0.005%

    No Known Activations