© 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. 14104
    Prev
    Next
    INDEX
    Explanations

    Armenian language and people

    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
    IBM
    -0.20
     IBM
    -0.19
    ible
    -0.19
    าย
    -0.19
     Iowa
    -0.18
    é¹Ĭ
    -0.18
    IB
    -0.18
    è¾½
    -0.18
    滨海
    -0.18
    é¼ĵ
    -0.17
    POSITIVE LOGITS
     Armenian
    0.50
     Armenia
    0.36
     Armen
    0.36
    æ°IJ
    0.26
    å½Ŀ
    0.26
     Azerbaijan
    0.25
     Sark
    0.25
     Azerbai
    0.25
    æ¸ij
    0.24
     Lebanese
    0.24
    Activations Density 0.067%

    No Known Activations