© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17241
    Prev
    Next
    INDEX
    Explanations

    like, likes, liked, or the like

    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
    Negative Logits
    ä½łçľĭ
    -0.17
    tle
    -0.17
    漫éķ¿çļĦ
    -0.16
    иÑĩеÑģки
    -0.15
    icamente
    -0.15
    ä¸ĸ家
    -0.15
    æĻ°
    -0.15
    cies
    -0.15
    portun
    -0.15
    _CHAIN
    -0.15
    POSITIVE LOGITS
    ably
    0.25
    able
    0.19
    ewise
    0.19
    -minded
    0.19
    hood
    0.19
    nowled
    0.19
    nap
    0.18
    ewood
    0.18
    heet
    0.17
    oney
    0.17
    Activations Density 0.013%

    No Known Activations