© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7373
    Prev
    Next
    INDEX
    Explanations

    states of comparison or intensity

    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
    èĢĮä¸Ķè¿ĺ
    -0.10
    è¦ģæĥ³
    -0.10
    à¹Ģà¸ī
    -0.09
    åIJĮæĹ¶ä¹Ł
    -0.09
    çĺģ
    -0.08
    约åIJĪ
    -0.08
    è®ĵä»ĸåĢij
    -0.08
    è®ĵä»ĸ
    -0.08
    å°ıå°ıçļĦ
    -0.08
    ä¿Ĺè¯Ŀ说
    -0.08
    POSITIVE LOGITS
     during
    0.14
    å¹³æŶ
    0.11
    during
    0.11
     durante
    0.11
    æĹ¥å¸¸
    0.11
     when
    0.10
     khi
    0.10
    åľ¨åºĬä¸Ĭ
    0.10
    ä¸Ģå®ļç¨ĭ度
    0.09
     أثÙĨاء
    0.09
    Activations Density 1.004%

    No Known Activations