© 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. 16752
    Prev
    Next
    INDEX
    Explanations

    both of

    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¿Ļæł·ä¸Ģ个
    -0.20
     aka
    -0.18
    among
    -0.17
     vÃłi
    -0.17
    åIJ¸å¼ķåĬĽ
    -0.17
    ılm
    -0.17
    ListModel
    -0.17
    ãģªãģ©ãģĮ
    -0.17
    ãģĮãĤī
    -0.17
    rab
    -0.16
    POSITIVE LOGITS
     sexes
    0.27
    æĪĸå¤ļ
    0.26
    åıĮåıĮ
    0.24
     alike
    0.23
    éĥ½æĺ¯
    0.23
    俱
    0.23
    æĪijéĥ½
    0.22
    éĥ½åĸľæ¬¢
    0.22
    åIJĦèĩª
    0.21
    éĥ½æľī
    0.21
    Activations Density 0.058%

    No Known Activations