© 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. 12257
    Prev
    Next
    INDEX
    Explanations

    weather resistance

    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
    æ¼ī
    -0.23
    åı¯ä»¥å¸®åĬ©
    -0.22
    ERVE
    -0.22
    çĬĬ
    -0.21
    帽åŃIJ
    -0.21
    踩
    -0.20
    æݨå¼Ģ
    -0.20
    éĻ·
    -0.20
    apult
    -0.20
     Miner
    -0.19
    POSITIVE LOGITS
    éĢIJå¹´
    0.24
    èħIJèļĢ
    0.24
    ä¹ħäºĨ
    0.23
    èĢģåĮĸ
    0.23
     маÑĤеÑĢиалов
    0.23
    æĿIJè´¨
    0.22
     outdoor
    0.21
    ç»Ī身
    0.21
     Outdoor
    0.21
    æĪ·å¤ĸ
    0.20
    Activations Density 0.019%

    No Known Activations