© 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. 8105
    Prev
    Next
    INDEX
    Explanations

    on the one hand, ..., on the other

    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¸įå°ı
    -0.11
    åĬ¨æĦŁ
    -0.11
    æĢĻ
    -0.09
    ovel
    -0.08
    yped
    -0.08
     Alone
    -0.08
    ç»ĻåĩºäºĨ
    -0.08
     jon
    -0.08
    éĢIJæ¸IJ
    -0.08
    ä¿Ĺ
    -0.08
    POSITIVE LOGITS
    åıĪèĥ½
    0.11
    åıĪ
    0.10
    å·¨
    0.10
    æľīæŶ
    0.10
    åıĪæĺ¯
    0.10
    åıĪè¦ģ
    0.09
    åīįä¸Ģ天
    0.09
    æĪijåıĪ
    0.09
    รา
    0.09
     birkaç
    0.09
    Activations Density 0.062%

    No Known Activations