© 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. 14113
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    è¿Ļ个åIJįåŃĹ
    -0.21
    anine
    -0.20
    Watching
    -0.20
    åŀ¸
    -0.20
    æĴķ
    -0.20
    çļĦåIJįåŃĹ
    -0.19
    åĥ®
    -0.18
    åIJįåŃĹ
    -0.18
    nda
    -0.18
    gon
    -0.18
    POSITIVE LOGITS
     symbols
    0.25
    符åı·
    0.24
    symbols
    0.23
    æĿĤ
    0.20
    é½IJåħ¨
    0.20
     punctuation
    0.20
     Symbols
    0.19
     педагог
    0.19
    符
    0.19
    饯
    0.19
    Activations Density 0.058%

    No Known Activations