© 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. 20652
    Prev
    Next
    INDEX
    Explanations

    including but not limited to

    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
    åĬ²
    -0.09
    尾巴
    -0.09
    erve
    -0.08
     Gor
    -0.08
    ponsored
    -0.08
    gor
    -0.08
    åij¨åĽ´çļĦ
    -0.08
    åĴĮæĬĢæľ¯
    -0.08
     Cly
    -0.08
    社ä¼ļåIJĦçķĮ
    -0.08
    POSITIVE LOGITS
    ä¸įæİĴéĻ¤
    0.13
    ä½Ĩä¸įéĻIJäºİ
    0.12
    ä½Ĩä¸įéĻIJ
    0.11
    åĨĴ
    0.11
    ä¸įå¤ļ
    0.09
    æĭİ
    0.09
    ä¸įçķĻ
    0.08
    ä¸įä»ħä»ħæĺ¯
    0.08
     divorced
    0.08
    ä¼
    0.08
    Activations Density 0.030%

    No Known Activations