© 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. 39141
    Prev
    Next
    INDEX
    Explanations

    cherish/cherished

    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
    illon
    -0.09
    çĸı
    -0.09
    å®ŀè´¨æĢ§
    -0.09
     Sach
    -0.08
    å·´åŁº
    -0.08
    åįĥéĩĮ
    -0.08
    èĩªçIJĨ
    -0.08
    	extern
    -0.08
    sw
    -0.08
    lands
    -0.08
    POSITIVE LOGITS
    éĤ£ä»½
    0.12
    åĭĥåĭĥ
    0.10
    ably
    0.10
    è¿Ļä¸ĢåĪ»
    0.10
    atory
    0.10
    æ¯ıä¸Ģ天
    0.09
    åķ¬
    0.09
    çĿĢ
    0.09
    éļ¾å¾Ĺ
    0.09
    å¢Ļä¸Ĭ
    0.09
    Activations Density 0.005%

    No Known Activations