© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12245
    Prev
    Next
    INDEX
    Explanations

    bird species

    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
    åłĨ积
    -0.24
    abad
    -0.23
    org
    -0.21
    æµ·åºķ
    -0.21
    snake
    -0.20
    洪水
    -0.20
     Patton
    -0.19
    æ»ļåĬ¨
    -0.19
    ogi
    -0.19
     meltdown
    -0.18
    POSITIVE LOGITS
    鸣类
    0.45
     birds
    0.42
     bird
    0.40
    å°ı鸣
    0.38
    鸣
    0.37
    é³¥
    0.35
    Bird
    0.35
     Bird
    0.35
    bird
    0.34
    åķĦ
    0.34
    Activations Density 0.080%

    No Known Activations