© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15161
    Prev
    Next
    INDEX
    Explanations

    literary works and authors

    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
    ÑĢеги
    -0.33
    æīĢæľīæĥħèĬĤ
    -0.33
    благо
    -0.32
    ãģĬäºĴ
    -0.28
    ãĤ¢ãĤ¤ãĥĨ
    -0.28
    å©»
    -0.28
    móvel
    -0.28
    ãĤŃãĥ£ãĥ³ãĥļ
    -0.27
     пÑĢиÑıÑĤн
    -0.27
    индивид
    -0.27
    POSITIVE LOGITS
    åĨĻä½ľ
    0.39
    è¯ĹæŃĮ
    0.35
     poetry
    0.34
     prose
    0.34
    æĸĩåѦ
    0.33
    ä½ľå®¶
    0.32
     literary
    0.32
    读èĢħ
    0.31
     poet
    0.30
    æķ£æĸĩ
    0.29
    Activations Density 0.157%

    No Known Activations