© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16667
    Prev
    Next
    INDEX
    Explanations

    El Paso, Texas

    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
    Ñģон
    -0.19
    æ±¹
    -0.19
    岸边
    -0.18
     lá»ĩ
    -0.18
    箬
    -0.17
    iki
    -0.17
    æŃ£åĵģ
    -0.17
    楫
    -0.17
    汨
    -0.16
    æ¡¡
    -0.16
    POSITIVE LOGITS
    aroo
    0.22
    èįĴ
    0.21
    ä»İ容
    0.20
    halb
    0.20
    é«ĺåİŁ
    0.19
    楼
    0.19
    æ²Ļæ¼ł
    0.19
    ä¸Ŀè·¯
    0.18
    åħµåĽ¢
    0.18
    edBy
    0.18
    Activations Density 0.005%

    No Known Activations