© 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. 12603
    Prev
    Next
    INDEX
    Explanations

    CTO

    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
    åı¯ä»¥è¯´
    -0.21
    æĺİæĺ¾çļĦ
    -0.21
    羦
    -0.20
    äºĽ
    -0.19
    çļĦè¯Ŀé¢ĺ
    -0.18
    ÑĩÑĥ
    -0.18
    èµŀæĪIJ
    -0.18
    åĬĿ
    -0.18
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.18
     perc
    -0.18
    POSITIVE LOGITS
    anager
    0.19
    outu
    0.19
    rens
    0.19
    chg
    0.19
    chest
    0.18
     Inherits
    0.18
     bergen
    0.18
    .addButton
    0.18
    lle
    0.18
    ellen
    0.18
    Activations Density 0.213%

    No Known Activations