© 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. 12130
    Prev
    Next
    INDEX
    Explanations

    source for

    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
    uito
    -0.18
    å¾Ī好
    -0.17
    observe
    -0.17
    æĬķåħ¥ä½¿çĶ¨
    -0.17
    uest
    -0.17
    å¾Īæĥ³
    -0.17
    UEST
    -0.17
    ãĥĻãĤ¹ãĥĪ
    -0.17
    說話
    -0.17
    trap
    -0.17
    POSITIVE LOGITS
    ä¿¡èµĸ
    0.22
    çļĦä¸ĢéĿ¢
    0.22
    åľ°ä¸Ĭ
    0.21
    åIJ«
    0.21
    åı¯éĿł
    0.21
    ä¸Ģç«Ļå¼ı
    0.21
    åĵģè´¨
    0.20
    -guide
    0.20
    ertest
    0.19
    æ±ĩèģļ
    0.19
    Activations Density 0.033%

    No Known Activations