© 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. 11272
    Prev
    Next
    INDEX
    Explanations

    Middle Eastern countries

    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
    RD
    -0.19
    æĮij
    -0.19
    éº»æľ¨
    -0.19
    女ç¥ŀ
    -0.19
    ä¸ĭæ²ī
    -0.18
    æľ¬èĥ½
    -0.18
    åħ³éŨ
    -0.17
    大å¹ħ度
    -0.17
     exponentially
    -0.17
    GREE
    -0.17
    POSITIVE LOGITS
    _CHIP
    0.22
    adel
    0.21
    chor
    0.20
     Bought
    0.19
    egen
    0.19
    chen
    0.19
    .Addr
    0.19
    odial
    0.19
     flare
    0.19
     Bain
    0.18
    Activations Density 0.008%

    No Known Activations