© 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. 11796
    Prev
    Next
    INDEX
    Explanations

    is the

    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
    å¾Īéĩįè¦ģ
    -0.19
    çĶ¨æĪ·æıIJä¾Ľ
    -0.19
    å¾Ī大
    -0.18
    å°ıåŃ©åŃIJ
    -0.18
    ãģľ
    -0.18
    ServiceProvider
    -0.18
    ä¸Ģ次æĢ§
    -0.17
    缴è¾ĸå¸Ĥ
    -0.17
     Freem
    -0.17
    ä¸ĢåĿĹ
    -0.17
    POSITIVE LOGITS
    çļĦåij½è¿IJ
    0.25
    ä»ĸ对
    0.21
     fate
    0.19
     اÙĦØŃاÙĦ
    0.18
    æĪijåľ¨
    0.18
     pem
    0.17
    ball
    0.17
    è¯Ŀ说
    0.17
    adia
    0.17
     обÑĢазом
    0.17
    Activations Density 0.016%

    No Known Activations