© 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. 15690
    Prev
    Next
    INDEX
    Explanations

    North Korea and Germany

    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
    å¢ŀåĢ¼
    -0.19
    ä¸Ńåįİæ°ijæĹı
    -0.19
    天使
    -0.19
    ä¸į失
    -0.18
    åį¿
    -0.18
    ittings
    -0.18
    èĪĴå¿ĥ
    -0.18
    èĩĬ
    -0.18
    èĪĴæľį
    -0.17
    çģ¼
    -0.17
    POSITIVE LOGITS
     Pyongyang
    0.21
    -border
    0.20
    kre
    0.19
    ç²®é£Ł
    0.19
    wij
    0.19
    оÑĢо
    0.18
     >>↵↵
    0.18
    Ñģком
    0.18
    æł·åŃIJ
    0.17
    æľĿé²ľ
    0.17
    Activations Density 0.006%

    No Known Activations