© 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. 16409
    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
    åIJĥä»Ģä¹Ī
    -0.20
     wom
    -0.20
    çıĤ
    -0.20
     {?}
    -0.19
    ä¸Ģç§Ĵ
    -0.18
    reaction
    -0.18
    æľīçļĦçݩ家
    -0.18
    éĺij
    -0.18
    ifice
    -0.18
    å¨ĺå¨ĺ
    -0.18
    POSITIVE LOGITS
    ÃľR
    0.21
    çıį
    0.20
    bon
    0.19
     bon
    0.18
    lix
    0.18
    .Linked
    0.18
    åħħ
    0.18
    ä¼Ĺ
    0.18
    éĽĦ
    0.18
    åħįè´£
    0.18
    Activations Density 0.000%

    No Known Activations