© 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. 13724
    Prev
    Next
    INDEX
    Explanations

    metropolitan areas and expansion

    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
    è¿Ļ家åħ¬åı¸
    -0.25
    .enumer
    -0.23
    åħļæĶ¯éĥ¨
    -0.23
    æīĵæī°
    -0.22
    åħ¬å¼Ģåıij
    -0.21
    çıIJ
    -0.21
    éĻĪè¿°
    -0.20
    å¼Ħ
    -0.20
    éĢļåijĬ
    -0.20
    顾
    -0.20
    POSITIVE LOGITS
    èĨ¨èĥĢ
    0.25
    åŁİå¸Ĥ群
    0.24
     sprawling
    0.24
    à¹ĥหà¸į
    0.23
    æī©å¼ł
    0.23
    æī©å®¹
    0.23
    ä¸įæĸŃæī©å¤§
    0.22
    人åı£
    0.22
     expansion
    0.22
    è¶ĬæĿ¥è¶Ĭ大
    0.21
    Activations Density 0.059%

    No Known Activations