© 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. 13961
    Prev
    Next
    INDEX
    Explanations

    examples, one, like, they, he, the

    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
    plus
    -0.23
    è¿Ļä¹Łæĺ¯
    -0.20
    æĽ´ä½ķåĨµ
    -0.20
    minus
    -0.20
    ãģ¾ãģŁ
    -0.20
    æĢ»ä¹ĭ
    -0.20
    FilterWhere
    -0.19
    åı¦å¤ĸ
    -0.19
    lius
    -0.19
    æѤå¤ĸ
    -0.19
    POSITIVE LOGITS
    åĽłåħ¶
    0.25
    对åħ¶
    0.23
    以åħ¶
    0.22
    éĢĭ
    0.22
    rum
    0.21
    åľ¨åħ¶
    0.20
    르
    0.18
     its
    0.18
    为äºĨæĽ´å¥½
    0.17
     itself
    0.17
    Activations Density 0.839%

    No Known Activations