© 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. 11636
    Prev
    Next
    INDEX
    Explanations

    different classes or types

    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
    ä¸įå®ļ
    -0.21
    ä¸ĢåĪĨéĴŁ
    -0.19
    è¶³å¤Ł
    -0.19
    åĬ¬
    -0.19
     another
    -0.18
    ä»»ä½ķå½¢å¼ı
    -0.18
    _SAMPLES
    -0.18
     bur
    -0.18
    åį¸
    -0.17
    赶
    -0.17
    POSITIVE LOGITS
    åIJĦèĩª
    0.42
    åIJĦèĩªçļĦ
    0.38
    åIJĦæľī
    0.38
    ä¸įåIJĮçļĦ
    0.34
     respective
    0.34
    åĪĨåĪ«
    0.33
    æľīä¸įåIJĮçļĦ
    0.32
    ãģĿãĤĮãģŀãĤĮ
    0.32
    çī¹å®ļ
    0.30
     specific
    0.28
    Activations Density 0.277%

    No Known Activations