© 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. 17177
    Prev
    Next
    INDEX
    Explanations

    Story highlights

    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
    orld
    -0.21
    å·²ä¹ħ
    -0.20
    ç»Ŀ
    -0.20
    æ¿Ĵ
    -0.20
    nia
    -0.18
    anie
    -0.18
    ACLE
    -0.18
     biod
    -0.18
    æ´»å¾Ĺ
    -0.18
     tas
    -0.18
    POSITIVE LOGITS
    iqu
    0.19
    éĢĢ
    0.19
    çĶµä»·
    0.19
    èķī
    0.18
    æ¶Ī
    0.18
    çªĴæģ¯
    0.18
    asin
    0.18
    ä¿İ
    0.18
    InputElement
    0.18
     Edu
    0.17
    Activations Density 0.007%

    No Known Activations