© 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. 14849
    Prev
    Next
    INDEX
    Explanations

    physical size and dimensions

    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
    å°¸
    -0.21
     SF
    -0.19
    VILLE
    -0.19
     sf
    -0.18
    è¿Ļåĩłå¹´
    -0.18
    .Named
    -0.18
    ausal
    -0.18
    æĭĵ
    -0.18
     pseud
    -0.18
    (Spring
    -0.18
    POSITIVE LOGITS
    ä½ĵ积
    0.26
    åįłåľ°éĿ¢ç§¯
    0.24
    size
    0.24
    æľºèº«
    0.23
    å¤ĸå½¢
    0.23
    尺寸
    0.22
     size
    0.21
    shape
    0.21
    主ä½ĵ
    0.21
    ä½ĵåŀĭ
    0.20
    Activations Density 0.058%

    No Known Activations