© 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. 13272
    Prev
    Next
    INDEX
    Explanations

    please followed by a verb

    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
    ever
    -0.22
    é¡·
    -0.19
    ä¸įä½Ĩ
    -0.19
    hood
    -0.18
    iful
    -0.18
    locked
    -0.18
     twice
    -0.18
    ier
    -0.17
    Äı
    -0.17
    åIJİæĿ¥
    -0.17
    POSITIVE LOGITS
    æĦŁåħ´è¶£
    0.21
    åĢ¼å¾Ĺ注æĦı
    0.21
    请注æĦı
    0.21
     note
    0.20
    大家åĪĨ享
    0.20
    æĦŁåħ´è¶£çļĦ
    0.20
    itar
    0.20
    注æĦı
    0.19
    è°¨æħİ
    0.19
    หาà¸ģ
    0.18
    Activations Density 0.012%

    No Known Activations