© 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. 10319
    Prev
    Next
    INDEX
    Explanations

    Home / navigation

    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
    èĢģå¸ĪçļĦ
    -0.20
    Slide
    -0.18
    åĿļ
    -0.18
    å®ĮæĪIJäºĨ
    -0.18
    åĵģçīĮçļĦ
    -0.18
    egl
    -0.18
    产çĶŁçļĦ
    -0.17
    åħ¸åŀĭçļĦ
    -0.17
    è¿ĻæĶ¯
    -0.17
    æ§Ĭ
    -0.17
    POSITIVE LOGITS
    èIJ±
    0.20
    稳
    0.19
    _decor
    0.18
     Crew
    0.18
     compens
    0.18
    ìĺ¤
    0.18
    å¸ĺ
    0.18
    اÙħÙĬ
    0.18
    è¿Ķ乡
    0.18
    è¡¥åģ¿
    0.18
    Activations Density 0.004%

    No Known Activations