© 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. 14874
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
     Mund
    -0.20
    æī«ä¸Ģæī«
    -0.19
    æļ§
    -0.19
    åĬ¨
    -0.18
     gạo
    -0.18
    åIJ¸éĻĦ
    -0.18
    æ¥ŀ
    -0.18
    å¾Ģ
    -0.18
    INGS
    -0.17
    æĺ
    -0.17
    POSITIVE LOGITS
    è¯Ńæ°Ķ
    0.21
    ä¸Ģåı¥è¯Ŀ
    0.20
    sentence
    0.19
    /question
    0.19
     sentence
    0.19
     sentences
    0.19
    rets
    0.19
    åı¥åŃIJ
    0.18
    -ending
    0.18
    iline
    0.18
    Activations Density 0.053%

    No Known Activations