© 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
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15921
    Prev
    Next
    INDEX
    Explanations

    debate, speech, arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     инÑĦоÑĢмаÑĨии
    -0.19
    åľ¨æķ´ä¸ª
    -0.19
    ãģ¦ãģĦãģį
    -0.19
    æ°ijå¿ĥ
    -0.18
    åĥıç´ł
    -0.18
    elf
    -0.18
    嵬
    -0.18
    åºĶæĶ¶
    -0.18
    RELEASE
    -0.18
    æĸ°åĬ¨èĥ½
    -0.18
    POSITIVE LOGITS
    辩论
    0.23
    辩
    0.22
     arguments
    0.22
     speeches
    0.22
    (argument
    0.21
    åı°ä¸Ĭ
    0.20
     heats
    0.20
    æĬĢå·§
    0.20
    对ç«ĭ
    0.20
     hydrated
    0.19
    Activations Density 0.017%

    No Known Activations