© 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. 13128
    Prev
    Next
    INDEX
    Explanations

    Iraq and Baghdad

    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
    蹬
    -0.20
    åľ°äº§
    -0.20
    éĥ½æĥ³
    -0.20
    æıĨ
    -0.20
    çĻ»å±±
    -0.19
    nc
    -0.19
     skiing
    -0.18
    éºĵ
    -0.18
    nature
    -0.18
    åĸĦæĦı
    -0.18
    POSITIVE LOGITS
    ä¼Ĭæĭīåħĭ
    0.34
     Iraqi
    0.33
    Iraq
    0.32
     Baghdad
    0.32
     Iraq
    0.32
     اÙĦعراÙĤ
    0.31
     Saddam
    0.30
     Mosul
    0.27
     اÙĦعراÙĤÙĬ
    0.25
     Kurdistan
    0.24
    Activations Density 0.032%

    No Known Activations