© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16960
    Prev
    Next
    INDEX
    Explanations

    Public Policy and Administration

    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
    对å¤ĸ
    -0.23
    形象
    -0.20
    éĻĮ
    -0.20
    åºĬä¸Ĭ
    -0.20
    AINED
    -0.20
    è·Łè¿Ľ
    -0.19
    åĨĢ
    -0.19
    çĿ¨
    -0.19
    æłĩ
    -0.19
    æ²¹çĶ»
    -0.18
    POSITIVE LOGITS
    丼
    0.23
     Hatch
    0.21
    (policy
    0.20
    èľ»
    0.20
     polÃŃt
    0.20
    æĶ¿
    0.20
    åѦä½į
    0.20
     cum
    0.19
    åħ¬åħ±
    0.19
     Degrees
    0.19
    Activations Density 0.037%

    No Known Activations