© 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. 16247
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    bra
    -0.21
    é«ĺä»·
    -0.21
    anal
    -0.20
    æ°¸ä¹ħ
    -0.19
    æ¡ĥ
    -0.19
     Bra
    -0.19
    ÓĢ
    -0.19
    ä»·
    -0.18
    æĪijçļĦå¿ĥ
    -0.18
     haz
    -0.18
    POSITIVE LOGITS
     Reef
    0.20
    èĩ¾
    0.20
    -sama
    0.20
    §
    0.20
    åįıåĬŀ
    0.19
    essenger
    0.18
    สะ
    0.18
    ä¸¥æł¼èIJ½å®ŀ
    0.18
    _Api
    0.18
    IBE
    0.18
    Activations Density 0.000%

    No Known Activations