© 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. 14567
    Prev
    Next
    INDEX
    Explanations

    doubling up, both, two, bilateral, consecutively

    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£å²¸
    -0.22
    éĿ¢ç§¯
    -0.21
    åĢŃ
    -0.20
    asier
    -0.20
    顽
    -0.20
    ç¼Ĺ
    -0.20
    éĿ¢ç§¯çº¦
    -0.19
    æĬ¼éĩij
    -0.19
    çĪ½
    -0.18
    INU
    -0.18
    POSITIVE LOGITS
     consecutive
    0.26
    åľ¨åIJĮä¸Ģ
    0.23
    åIJĮæŶ
    0.21
    ump
    0.21
    ä¸Ģ天
    0.21
    åIJĮä¸Ģ
    0.21
    缸继
    0.20
     Calder
    0.20
    emet
    0.19
    keit
    0.19
    Activations Density 0.042%

    No Known Activations