© 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. 11680
    Prev
    Next
    INDEX
    Explanations

    is / are followed by description

    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
    æĺ¯ä¸Ģç§į
    -0.20
     ci
    -0.19
    çļĦæĺ¯
    -0.18
    æĺ¯ä¸įä¼ļ
    -0.18
    械
    -0.18
    å¼ıçļĦ
    -0.18
    éĤ£å°±
    -0.18
    iston
    -0.17
    sert
    -0.17
    æĺ¯ä¸ª
    -0.17
    POSITIVE LOGITS
    ä¸įåIJĪéĢĤ
    0.19
    edor
    0.18
    åıĤä¸İåĪ°
    0.17
    SURE
    0.17
    éĹ®é¢ĺæĺ¯
    0.17
    æĸĩåĮĸåĴĮ
    0.17
    æľįåĬ¡æľºæŀĦ
    0.17
    è¿ijäºĽ
    0.16
     previously
    0.16
    åĪĽæĸ°åıijå±ķ
    0.16
    Activations Density 0.172%

    No Known Activations