© 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. 49839
    Prev
    Next
    INDEX
    Explanations

    followed by sentence start

    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
    æŶ任
    -0.10
    ç»ıå¼Ģ
    -0.09
    ÑĮÑİ
    -0.09
    æľīæŶ
    -0.09
    icer
    -0.08
    å¸Ĥåľºä»·æł¼
    -0.08
    åıĹä¸įäºĨ
    -0.08
    论
    -0.08
     comple
    -0.08
    åłĤ
    -0.08
    POSITIVE LOGITS
    å±ĬæŶ
    0.11
    æĺİå¹´
    0.11
     Likely
    0.10
     Sham
    0.10
    ä¸İæѤ
    0.10
     ÑģкоÑĢо
    0.10
    æѤåĪ»
    0.10
     upcoming
    0.10
    äºİæѤ
    0.10
    åīįæĻ¯
    0.10
    Activations Density 0.248%

    No Known Activations