© 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. 15716
    Prev
    Next
    INDEX
    Explanations

    World War II

    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
    annual
    -0.21
    常年
    -0.21
     skate
    -0.20
     annual
    -0.20
    æģŃæķ¬
    -0.20
    ä¸Ģé¡¿
    -0.19
     Terrorism
    -0.19
    åĪĥ
    -0.19
     annually
    -0.18
     Abu
    -0.18
    POSITIVE LOGITS
    æĬĹæĪĺ
    0.36
     wartime
    0.29
    æĶ¯æı´
    0.28
    æĬĹæĹ¥
    0.27
     war
    0.26
    äºĮæĪĺ
    0.25
    -war
    0.25
     requis
    0.24
    è®Ńç»ĥ
    0.23
    èĭıèģĶ
    0.22
    Activations Density 0.110%

    No Known Activations