© 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. 16044
    Prev
    Next
    INDEX
    Explanations

    lie, lies, lying, liar

    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
    æ¯ĵ
    -0.23
    éħ¸
    -0.21
    ipes
    -0.21
    èļĮ
    -0.18
    è¿ĻæĶ¯
    -0.18
     ÑģÑĢед
    -0.18
     Mov
    -0.18
    áĥ«
    -0.18
    çļĦè¿ĽæŃ¥
    -0.18
    éĿĴæĺ¥æľŁ
    -0.18
    POSITIVE LOGITS
    è°İè¨Ģ
    0.38
    è°İ
    0.36
    çŀĴ
    0.36
    èĻļåģĩ
    0.35
    éļIJçŀĴ
    0.34
     falsehood
    0.31
    truth
    0.30
     truth
    0.30
    欺è¯Ī
    0.29
    Truth
    0.29
    Activations Density 0.087%

    No Known Activations