© 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. 13387
    Prev
    Next
    INDEX
    Explanations

    dates before "by" or "at"

    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
    ä¼
    -0.22
    åĹĦ
    -0.18
    iska
    -0.18
    ugs
    -0.18
    æĥº
    -0.18
     Tig
    -0.17
    CVE
    -0.17
    åı£æ°´
    -0.17
    鸩
    -0.17
    å¼ĤæĢ§
    -0.17
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.19
    èĮħ
    0.17
    ç©¿è¶Ĭ
    0.16
     Coy
    0.16
    èĩªè±ª
    0.16
    .ByteString
    0.16
    åį³
    0.16
    æĭIJ
    0.16
    ä¸įå°ı
    0.15
     Ø£ØŃ
    0.15
    Activations Density 0.045%

    No Known Activations