© 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. 12516
    Prev
    Next
    INDEX
    Explanations

    statistics following numbers

    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
    :before
    -0.21
    ä¸į代表
    -0.18
     places
    -0.18
    &E
    -0.18
    çĽ¸ä¼ł
    -0.18
     justified
    -0.18
    -selector
    -0.17
    ги
    -0.17
    ("'"
    -0.17
     downt
    -0.16
    POSITIVE LOGITS
    æĪĺ绩
    0.23
    å¥¹åľ¨
    0.22
    éĻĨåĨĽ
    0.20
    åIJĮæŶè¿ĺ
    0.19
    è¿ĻäºĽéĥ½æĺ¯
    0.19
    åı¯ä»¥è¯´æĺ¯
    0.19
    éħIJ
    0.19
    око
    0.18
    缸åħ³æĸ°éĹ»
    0.18
    _MISC
    0.18
    Activations Density 0.016%

    No Known Activations