© 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. 14854
    Prev
    Next
    INDEX
    Explanations

    European Union government

    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
    该åİ¿
    -0.23
    èģĺ请
    -0.21
    éĴĪ对æĢ§
    -0.21
    ä¸Ģè¶Ł
    -0.21
    åİ¿å§Ķ书记
    -0.20
    æıŃéľ²
    -0.20
    ä¿¡ç®±
    -0.20
    åŁİåĮº
    -0.20
    è¿Ļ个è¡Įä¸ļ
    -0.20
    à¹Ģล
    -0.20
    POSITIVE LOGITS
    ä¸Ģä½ĵåĮĸ
    0.26
    ä¸Ģä½ĵ
    0.22
    ç»Ĭ
    0.21
    ervo
    0.20
    uez
    0.19
    忪
    0.19
    vla
    0.19
    伸
    0.19
     weakest
    0.19
    éĩįå¿ĥ
    0.19
    Activations Density 0.022%

    No Known Activations