© 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. 51925
    Prev
    Next
    INDEX
    Explanations

    referring to people

    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
    å¾Ĺèµ·
    -0.10
    å¶
    -0.10
    çļĦç¼ĺ
    -0.09
    åĩĮ
    -0.09
    adoo
    -0.09
    諸
    -0.09
    åĤ¬
    -0.09
    çĤ¹äºĨ
    -0.09
    è¿Ļè¯Ŀ
    -0.09
    æ¯Ľæ³½ä¸ľ
    -0.09
    POSITIVE LOGITS
    æĬĬèĩªå·±çļĦ
    0.08
    icc
    0.08
    对æłĩ
    0.08
    ork
    0.08
    æ²½
    0.08
    帮åĬ©ä¼ģä¸ļ
    0.08
    对她
    0.07
    çĶŁæ´»æ°´å¹³
    0.07
     sy
    0.07
    .utility
    0.07
    Activations Density 0.005%

    No Known Activations