© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8615
    Prev
    Next
    INDEX
    Explanations

    PRESIDENT

    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
    ä¸Ĭå®ĺ
    -0.10
    å¼ĤæĢ§
    -0.10
    çļĦ好
    -0.10
    ebin
    -0.09
    æĭĻ
    -0.09
     sund
    -0.08
    çĿĩ
    -0.08
    _unset
    -0.08
    æ³Ĭ
    -0.08
    顶
    -0.08
    POSITIVE LOGITS
    åĪ°è¿ĻéĩĮ
    0.09
    æİ¥è¿ĩ
    0.09
    讲è¯Ŀ
    0.09
    æĪijæĥ³
    0.09
    åijĬè¯īè®°èĢħ
    0.09
    交è°Ī
    0.09
    åıijè¨Ģ
    0.09
    è¿ĺ没æľī
    0.09
    å½ĵçĦ¶æĺ¯
    0.08
    .opensource
    0.08
    Activations Density 0.055%

    No Known Activations