© 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. 14912
    Prev
    Next
    INDEX
    Explanations

    award recipients and members

    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
    å®īåħ¨æĢ§
    -0.25
     безопаÑģ
    -0.24
    åŁºæľ¬
    -0.24
    æij¸ç´¢
    -0.23
    å®īåħ¨
    -0.23
    æł¹æľ¬
    -0.23
    ä¸įåĪ©
    -0.23
     basics
    -0.23
    éĢ¼è¿ij
    -0.23
    à¸Ĥà¸Ļ
    -0.22
    POSITIVE LOGITS
    çĨł
    0.28
    anko
    0.26
     deserving
    0.26
    表彰
    0.26
    afort
    0.25
    èİ·å¥ĸ
    0.25
    æªĢ
    0.24
    èį£èªī称åı·
    0.24
    æİĪäºĪ
    0.24
    ä»»æľŁ
    0.23
    Activations Density 0.047%

    No Known Activations