© 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. 10794
    Prev
    Next
    INDEX
    Explanations

    men's sports

    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
    ece
    -0.20
    ORITY
    -0.20
    hus
    -0.19
    ths
    -0.19
    oley
    -0.19
    _li
    -0.19
    åĥļ
    -0.19
    ointments
    -0.18
     âĺĨ
    -0.18
     Norris
    -0.18
    POSITIVE LOGITS
    åŁºè°ĥ
    0.22
    å¹¼
    0.18
    ç³»ç»ŁçļĦ
    0.18
    æĶ¹éĿ©å§Ķ
    0.18
    管éģĵ
    0.18
    åij¼å£°
    0.18
    ç§ijæĬĢåĽŃ
    0.18
     nrw
    0.17
    -only
    0.17
    imensional
    0.17
    Activations Density 0.012%

    No Known Activations