© 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. 9129
    Prev
    Next
    INDEX
    Explanations

    Patent Appeal Circuit

    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
    ä¸¤åľ°
    -0.10
    å«Įå¼ĥ
    -0.09
    regor
    -0.09
    æ»ŀåIJİ
    -0.09
    èѦæĸ¹
    -0.09
     пÑĢизна
    -0.09
    éŁ³åĵį
    -0.09
    лаг
    -0.08
    æĪŁ
    -0.08
    ä¸ŃåĽ½äººæ°ij
    -0.08
    POSITIVE LOGITS
    çłĶ
    0.09
    å»Ĭ
    0.09
    èıĢ
    0.09
    沤
    0.09
    åł°
    0.09
    çªĴæģ¯
    0.08
    å¼Ģæ°´
    0.08
    å§Ķ
    0.08
    plib
    0.08
    INGTON
    0.08
    Activations Density 0.086%

    No Known Activations