© 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. 13837
    Prev
    Next
    INDEX
    Explanations

    six or four

    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
    äºĮèĢħ
    -0.35
    两èĢħ
    -0.34
    pdev
    -0.20
    ä¸īåĽĽ
    -0.20
    ·»
    -0.19
    èĨĤ
    -0.19
    illions
    -0.19
    两åıª
    -0.19
    两项
    -0.18
    äºĮåŃĹ
    -0.18
    POSITIVE LOGITS
    åĪĨåĪ«æĺ¯
    0.45
    åĪĨåĪ«ä¸º
    0.35
    ä¸įåIJĮç¨ĭ度
    0.33
    åĪĨåĪ«
    0.30
    ãģĿãĤĮãģŀãĤĮ
    0.29
    åIJĦæľī
    0.25
    ãģĨãģ¡
    0.24
    åIJĦèĩª
    0.23
    åIJĦå¼Ĥ
    0.23
    teen
    0.23
    Activations Density 0.584%

    No Known Activations