© 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. 11308
    Prev
    Next
    INDEX
    Explanations

    company names and titles

    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
    gmt
    -0.22
    па
    -0.21
    没äºĨ
    -0.21
    ä¸įåĥı
    -0.20
    åij¨åĪĬ
    -0.20
    åĽ°
    -0.19
    ights
    -0.19
    æķĻè®Ń
    -0.19
    ursor
    -0.18
    å°¤åħ¶æĺ¯
    -0.18
    POSITIVE LOGITS
    æĿ¥èĩª
    0.24
    æĻ®æĥł
    0.22
    纪å½ķ
    0.19
     bibli
    0.19
    ::_
    0.19
    ä¾Ĩèĩª
    0.19
    æģŃåĸľ
    0.19
    æĭ¿ä¸ĭ
    0.18
    ä¸Ģ群
    0.18
    èİ·èĥľ
    0.18
    Activations Density 0.054%

    No Known Activations