© 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. 20847
    Prev
    Next
    INDEX
    Explanations

    officials saying or doing things

    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
    æĻ¨æĬ¥
    -0.13
    lify
    -0.10
    èĢģ人家
    -0.10
    æĢ»åĨłåĨĽ
    -0.10
    lings
    -0.09
    çľ¼è§Ĵ
    -0.09
    大æ´ĭ
    -0.09
    иÑģ
    -0.09
    ç»ıèIJ¥æ´»åĬ¨
    -0.09
    èĢģçĻ¾å§ĵ
    -0.09
    POSITIVE LOGITS
    åĥļ
    0.11
    icient
    0.11
    dehyde
    0.10
    dom
    0.09
    emente
    0.09
    	TokenName
    0.09
    annes
    0.09
    们çļĦ
    0.09
    æĸ¯åŁº
    0.09
    ìĤ¬íķŃ
    0.09
    Activations Density 0.018%

    No Known Activations