© 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. 13392
    Prev
    Next
    INDEX
    Explanations

    violence and armed conflict

    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
    stor
    -0.21
    寮
    -0.21
     Enumeration
    -0.20
    è°Īè¯Ŀ
    -0.19
    èī¯
    -0.19
    dbname
    -0.19
    gger
    -0.18
    æĬľãģij
    -0.18
    è·Įå¹ħ
    -0.18
    éĵĭ
    -0.18
    POSITIVE LOGITS
    æīĭ段
    0.27
    EIF
    0.20
    /power
    0.19
    æļ´åĬĽ
    0.19
    forcement
    0.19
    	Mono
    0.18
     violence
    0.18
    çļĦåĬĽéĩı
    0.18
    /me
    0.18
    åĬĽæ°Ķ
    0.18
    Activations Density 0.038%

    No Known Activations