© 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. 13884
    Prev
    Next
    INDEX
    Explanations

    contractor, exec, court, sold

    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
    yer
    -0.19
    ÃŃt
    -0.19
     potent
    -0.19
    ä¸įèĩ³äºİ
    -0.18
    _least
    -0.18
    биÑĤ
    -0.18
    igt
    -0.18
    ollywood
    -0.18
     periods
    -0.18
     habits
    -0.17
    POSITIVE LOGITS
    è´Łè´£
    0.25
    æĬĢæľ¯åĴĮ
    0.23
    åħ·ä½ĵ
    0.23
    åħ±åIJĮ
    0.21
    è¯¥æł¡
    0.20
    æĻ®æĥł
    0.20
    ç»Ħç»ĩå®ŀæĸ½
    0.20
    æī¿åĬŀ
    0.20
    ç§ijåѦæĬĢæľ¯
    0.20
    å½Ĵå±ŀ
    0.20
    Activations Density 0.076%

    No Known Activations