© 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. 14818
    Prev
    Next
    INDEX
    Explanations

    War, soldiers, and games

    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
    è¯Ŀé¢ĺ
    -0.20
    çĶŁæĦı
    -0.20
    hic
    -0.20
    çī©è´¨
    -0.19
    è¯Ŀ
    -0.19
     relations
    -0.18
    aisy
    -0.18
    çݳ
    -0.18
    èĴ¸
    -0.18
    quests
    -0.18
    POSITIVE LOGITS
    æįį
    0.22
    пÑģи
    0.21
    NESS
    0.20
    æ¯įæł¡
    0.20
    çĤ¹å¤ļ
    0.20
    dbuf
    0.19
    è¿Ļ款
    0.19
    ç«ŀäºī对æīĭ
    0.19
    éĺ´å½±
    0.18
    aal
    0.18
    Activations Density 0.006%

    No Known Activations