© 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. 10505
    Prev
    Next
    INDEX
    Explanations

    causes delays or limitations

    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
    åĽłä¸º
    -0.23
    åĽłä¸ºä½ł
    -0.23
    åĽłåħ¶
    -0.22
    åĽłä¸ºä»ĸ
    -0.21
    æł¹æį®èĩªå·±
    -0.21
    åĽł
    -0.21
    çĶ¨èĩªå·±çļĦ
    -0.20
    çĶ±äºİ
    -0.20
    andin
    -0.19
    _defs
    -0.19
    POSITIVE LOGITS
    使åħ¶
    0.27
    使å¾Ĺ
    0.25
    让å®ĥ
    0.25
    åĨ³å®ļäºĨ
    0.25
    è¿ĻæĿ¡è·¯
    0.20
    使ä¹ĭ
    0.20
    è¿Ļ项
    0.19
    èĢĹ
    0.19
    使
    0.19
    è¿Ļ款
    0.19
    Activations Density 0.181%

    No Known Activations