© 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. 16856
    Prev
    Next
    INDEX
    Explanations

    religious terms and government

    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
     Malk
    -0.21
    æĸ°çļĦä¸Ģ
    -0.19
    èĩªèIJ¥
    -0.19
    ÑĥÑĤÑĮ
    -0.19
    åİ¿å§Ķ书记
    -0.19
    matchCondition
    -0.18
    å¹²åĩĢ
    -0.18
     vad
    -0.18
    åĸĿäºĨ
    -0.18
    å¼ij
    -0.18
    POSITIVE LOGITS
    ä¸ĢéĹª
    0.24
    guard
    0.23
    å°ıåĦ¿
    0.21
    大ä¼Ĺ
    0.20
    å»
    0.20
    ừng
    0.20
    ophobic
    0.20
    éĢĢå¸Ĥ
    0.19
    åĵįèµ·
    0.19
    DRV
    0.18
    Activations Density 0.006%

    No Known Activations