© 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. 15415
    Prev
    Next
    INDEX
    Explanations

    opinion of the court

    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
    itty
    -0.20
    è¯ī
    -0.20
    è¿Ļæł·çļĦè¯Ŀ
    -0.19
    ä½łåĸľæ¬¢
    -0.18
    æĪijä»¬ä¹Ł
    -0.18
    代åĬŀ
    -0.18
    è¡į
    -0.18
     ÑģамоÑģÑĤоÑıÑĤелÑĮно
    -0.18
     Mog
    -0.18
    esty
    -0.17
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.20
    åħ°èĬ±
    0.18
    inha
    0.18
    对æĪijæĿ¥è¯´
    0.18
    对她
    0.18
    åŀ¦
    0.18
    åĽ¢éĺŁ
    0.18
    ç»ĦåĽ¢
    0.18
    ambi
    0.17
    æĪIJåijĺ
    0.17
    Activations Density 0.023%

    No Known Activations