© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14952
    Prev
    Next
    INDEX
    Explanations

    hypocrisy and insincerity

    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
    ä¼łæĿ¥
    -0.19
    åīįæĻ¯
    -0.19
    å°ıæľĭåıĭ
    -0.19
    èIJ½ãģ¡
    -0.19
    éĺı
    -0.19
    von
    -0.18
    ä¸įåĩĨ
    -0.18
    ä¸įç¡®å®ļ
    -0.18
    æĸ°çļĦ
    -0.18
    çĸ¾çĹħçļĦ
    -0.17
    POSITIVE LOGITS
    ifiable
    0.19
    /il
    0.19
    åľ¨éĩĮéĿ¢
    0.18
    หมà¸Ķ
    0.18
    URED
    0.18
    /false
    0.18
    ä¹ĭå¤Ħ
    0.18
    adle
    0.18
    夸
    0.17
    arious
    0.17
    Activations Density 0.004%

    No Known Activations