© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12369
    Prev
    Next
    INDEX
    Explanations

    Japanese names and places

    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
    1
    -0.22
    3
    -0.22
    纽
    -0.21
    yn
    -0.21
    and
    -0.21
    C
    -0.20
    4
    -0.20
    æѤå¤Ħ
    -0.20
    All
    -0.20
    ../../../
    -0.20
    POSITIVE LOGITS
    åľ¨æĹ¥æľ¬
    0.50
    æĹ¥æľ¬
    0.44
     japanese
    0.42
    Japanese
    0.42
     Japanese
    0.41
    Japan
    0.38
     Japan
    0.38
    æĹ¥æľ¬äºº
    0.36
    ä¸ľäº¬
    0.35
    å®īåĢį
    0.34
    Activations Density 0.216%

    No Known Activations