© 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. 13973
    Prev
    Next
    INDEX
    Explanations

    just + following words

    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¸įä»ħ
    -0.26
    ä¸įä»ħè¦ģ
    -0.24
    ä¸įä»ħåı¯ä»¥
    -0.23
    ä¸įä»ħæĺ¯
    -0.21
    ä¸įåĥħ
    -0.20
    ä¸įä»ħä»ħæĺ¯
    -0.20
    æĹ¢æĺ¯
    -0.19
    ä¸į论æĺ¯
    -0.19
    éĻ¤äºĨ
    -0.18
    åĨł
    -0.18
    POSITIVE LOGITS
    æĤī
    0.22
    zag
    0.19
    èĢģ大
    0.18
    é¤į
    0.18
    dep
    0.18
    åįķ纯çļĦ
    0.18
     spo
    0.17
    wij
    0.17
    ifiable
    0.17
    conj
    0.17
    Activations Density 0.019%

    No Known Activations