© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16947
    Prev
    Next
    INDEX
    Explanations

    postponement or cancellation

    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
    åľ¨è¿ĩæ¸¡æľŁ
    -0.24
    åľ¨è¿ĩ渡
    -0.22
    èĥ¸æĢĢ
    -0.22
    ÑĮе
    -0.19
    onde
    -0.18
    _IOC
    -0.18
    رص
    -0.18
    _SCL
    -0.18
    istic
    -0.18
    istan
    -0.18
    POSITIVE LOGITS
    èĩ³
    0.23
    ä¸Ģåľº
    0.21
     due
    0.21
    arih
    0.20
    schedule
    0.20
    çĶ±äºİ
    0.20
    æĹ¥æľŁ
    0.19
    ä¸Ģ次
    0.19
    ä¸ĭåij¨
    0.19
    å¸Ń
    0.19
    Activations Density 0.017%

    No Known Activations