© 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. 13262
    Prev
    Next
    INDEX
    Explanations

    updates, announcements, and information

    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
    æī¾ä¸įåĪ°
    -0.21
    çľĭä¸įåĪ°
    -0.21
    çݯ氧
    -0.20
    è¿Ļä¹Īåģļ
    -0.20
    侮辱
    -0.20
    æĵİ
    -0.19
    gross
    -0.19
    lux
    -0.19
    ä¸įåħģ许
    -0.19
     erre
    -0.19
    POSITIVE LOGITS
    çİ°åľº
    0.24
    å½ĵåľº
    0.23
    æ°Ķæ°Ľ
    0.22
    æľªæĿ¥çļĦ
    0.22
     hopefully
    0.22
    讨论
    0.21
    æĸ°çļĦ
    0.21
    hopefully
    0.21
    éĿ¢å¯¹éĿ¢
    0.21
    åIJĦèĩª
    0.21
    Activations Density 0.100%

    No Known Activations