© 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. 14246
    Prev
    Next
    INDEX
    Explanations

    poly(glycol) chains polymers

    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
    NCY
    -0.24
    人åijĺ
    -0.23
    㶲
    -0.22
    ä¸įæŃ»
    -0.22
    èĩĢ
    -0.21
     Computing
    -0.20
    åĢ¼çıŃ
    -0.19
    æĢµ
    -0.19
    outu
    -0.19
    èĪIJ
    -0.19
    POSITIVE LOGITS
     chains
    0.24
     polymer
    0.24
     chain
    0.24
    opoly
    0.23
    éĵ¾
    0.23
    ç©¿æ¢Ń
    0.22
    poly
    0.21
    æĥŃ
    0.21
    ÑĪив
    0.20
     crossorigin
    0.20
    Activations Density 0.277%

    No Known Activations