© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 13804
    Prev
    Next
    INDEX
    Explanations

    refused, not

    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¯ıä¸Ģ个人
    -0.21
    charg
    -0.21
     scand
    -0.20
    æŃ£åĵģ
    -0.19
    ä¸įç®¡ä½ł
    -0.19
    æĺİåªļ
    -0.18
    äºĴè¡¥
    -0.18
    èİ«è¿ĩäºİ
    -0.18
    æ¯ıä½į
    -0.18
    è¡£
    -0.18
    POSITIVE LOGITS
    (choice
    0.22
    çļĦçIJĨçͱ
    0.22
    æĭĴç»Ŀ
    0.21
    èĢĮæĺ¯
    0.21
    æĭĴä¸į
    0.20
    uslim
    0.20
    /ref
    0.20
    esis
    0.20
    emain
    0.19
    çİ·
    0.19
    Activations Density 0.052%

    No Known Activations