© 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. 10595
    Prev
    Next
    INDEX
    Explanations

    classic followed by noun

    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
    åĹª
    -0.18
    eah
    -0.18
    ÙĦØ©
    -0.17
    oley
    -0.17
    æ·±åĪĩ
    -0.16
    aken
    -0.16
    ucch
    -0.16
     slightest
    -0.16
    blings
    -0.16
    ez
    -0.15
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.24
    ç»ıåħ¸çļĦ
    0.22
    -minded
    0.22
    -style
    0.22
    ä¹ĭä½ľ
    0.21
    ìłģìĿ¸
    0.21
    æĦıä¹īä¸Ĭ
    0.20
    /original
    0.19
    æĢ§çļĦ
    0.19
    ity
    0.19
    Activations Density 0.014%

    No Known Activations