© 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. 11025
    Prev
    Next
    INDEX
    Explanations

    Japan and Japanese

    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
    æ²®
    -0.19
    OrUpdate
    -0.19
    们
    -0.19
    ss
    -0.18
    ŀæĢ§
    -0.18
    们çļĦ
    -0.18
    nd
    -0.18
    å·´å·´
    -0.18
    ally
    -0.18
    ams
    -0.18
    POSITIVE LOGITS
    Japan
    0.22
    earch
    0.22
    ä¸ľäº¬
    0.21
    åľ¨æĹ¥æľ¬
    0.20
    樱èĬ±
    0.19
    -speaking
    0.19
    Japanese
    0.19
     NháºŃt
    0.19
    keit
    0.18
    å®īåĢį
    0.18
    Activations Density 0.023%

    No Known Activations