© 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. 11765
    Prev
    Next
    INDEX
    Explanations

    video

    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
    æŃ£æĸĩ
    -0.21
    æ·»
    -0.20
    å½ĵäºĭ
    -0.20
    wald
    -0.19
    uv
    -0.18
     ETA
    -0.18
    ä¸ĢäºĮ
    -0.18
    §
    -0.18
    inder
    -0.17
     lanc
    -0.17
    POSITIVE LOGITS
    è§Ĩé¢ij
    0.47
     video
    0.41
    video
    0.39
     videos
    0.38
     vÃŃdeo
    0.36
     видео
    0.35
    çļĦçĶ»éĿ¢
    0.33
    å½ķåĪ¶
    0.33
    -video
    0.33
     vidéo
    0.32
    Activations Density 0.236%

    No Known Activations