© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36611
    Prev
    Next
    INDEX
    Explanations

    ’s disease

    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
     Hew
    -0.10
    座è°Īä¼ļ
    -0.10
    gies
    -0.09
    å¨ĺå¨ĺ
    -0.09
    åĪĽæĸ°èĥ½åĬĽ
    -0.09
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.09
    çģŀ
    -0.09
    /question
    -0.09
    éªı
    -0.08
    æ¸ħæĺİ
    -0.08
    POSITIVE LOGITS
    æĹ¨
    0.09
    3
    0.08
    1
    0.08
    ç»Ŀ
    0.08
    å¤ļè¾¾
    0.08
    2
    0.07
    4
    0.07
    ç§ijæĬĢ大åѦ
    0.07
     Viktor
    0.07
     usur
    0.07
    Activations Density 0.012%

    No Known Activations