© 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. 13291
    Prev
    Next
    INDEX
    Explanations

    car and vehicle related contexts

    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
    èººåľ¨åºĬä¸Ĭ
    -0.23
    å¿ĥä¸ŃçļĦ
    -0.21
    æ¹Ľ
    -0.21
    æµ´
    -0.21
    该éĻ¢
    -0.19
    èĶĹ
    -0.19
    æĴij
    -0.19
    è¾¹ç¼ĺ
    -0.19
    该æĿij
    -0.19
    è¾ĪåŃIJ
    -0.19
    POSITIVE LOGITS
    åĨħçļĦ
    0.23
    éĩĮ
    0.22
    éĩĮçļĦ
    0.21
    èĥĮä¸Ĭ
    0.19
    å½ĵä½ľ
    0.19
    笼
    0.19
    æıī
    0.18
    åĨħ
    0.18
    MD
    0.18
    æĹħéĢĶ
    0.18
    Activations Density 0.019%

    No Known Activations