© 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. 15093
    Prev
    Next
    INDEX
    Explanations

    razor, city, red, zara

    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
    羯
    -0.22
    rub
    -0.20
    emy
    -0.18
    楫
    -0.18
    èįŀ
    -0.18
    å¹³æĸ¹
    -0.18
    antha
    -0.18
    ifer
    -0.17
    æªĶ
    -0.17
    usting
    -0.17
    POSITIVE LOGITS
    ä¸Ģçīĩ
    0.21
    åIJĦ项
    0.21
     irreversible
    0.21
    çļĦåIJĦ项
    0.21
    èĪ£
    0.19
    ç½ij讯
    0.18
    éĦŀ
    0.18
     retaining
    0.18
    trim
    0.18
     prefix
    0.17
    Activations Density 0.001%

    No Known Activations