© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 57101
    Prev
    Next
    INDEX
    Explanations

    Christian ethic and faith

    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
    æİ¨å´ĩ
    -0.11
    è¿Łè¿Ł
    -0.10
    责任å¿ĥ
    -0.09
    è¿Ŀ
    -0.09
    æĭ¿äºĨ
    -0.09
    é£Ĵ
    -0.09
    å¸Ĥåħ¬å®īå±Ģ
    -0.09
    çļĦåİĭåĬĽ
    -0.09
    çĬ¯ç½ª
    -0.09
    åĨĢ
    -0.09
    POSITIVE LOGITS
     dram
    0.09
    æ´¾
    0.08
    åľ¨å½ĵåľ°
    0.08
    åѵ
    0.08
     Ferm
    0.08
    åļ¼
    0.08
    å½±åĵįåĬĽ
    0.08
    ç®Ģç§°
    0.07
    ä¼łæĴŃ
    0.07
     Dram
    0.07
    Activations Density 0.035%

    No Known Activations