© 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. 10359
    Prev
    Next
    INDEX
    Explanations

    convenience or simplification

    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
    Negative Logits
    OptionsResolver
    -0.21
    峡
    -0.20
    IZER
    -0.19
    ponent
    -0.18
    SKI
    -0.18
    æĥŁ
    -0.18
    PropertyParams
    -0.17
    ERING
    -0.17
    å¾ĹäºĨ
    -0.17
    JC
    -0.17
    POSITIVE LOGITS
     convenience
    0.25
    asher
    0.23
    便æį·
    0.22
     Convenience
    0.22
    ä¸į便
    0.21
    æĸ¹ä¾¿
    0.21
     Convenient
    0.21
    便åĪ©
    0.20
    ä¹ĭä¸ĭ
    0.19
     convenient
    0.19
    Activations Density 0.016%

    No Known Activations