© 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. 13165
    Prev
    Next
    INDEX
    Explanations

    food preparation involving specific ingredients

    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
    .backend
    -0.20
     iy
    -0.20
    åİ©
    -0.19
    _DEN
    -0.19
     Cour
    -0.19
     tÃł
    -0.18
    è¿ŀè½½
    -0.18
    _CM
    -0.18
    amu
    -0.18
    +v
    -0.18
    POSITIVE LOGITS
    ä¸ļ
    0.24
     tiá»ĩn
    0.22
    æ¥Ń
    0.21
    æĢ»åħ¬åı¸
    0.21
     èĩªåĬ¨çĶŁæĪIJ
    0.21
    å¾Īæĸ¹ä¾¿
    0.21
    类产åĵģ
    0.21
     Convenience
    0.21
     convenience
    0.20
     завод
    0.20
    Activations Density 0.017%

    No Known Activations