© 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. 14753
    Prev
    Next
    INDEX
    Explanations

    New York Times

    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
    TURE
    -0.18
    _SDK
    -0.17
    ernet
    -0.17
     khÃŃ
    -0.17
    avigate
    -0.17
    ĺ认
    -0.17
    _native
    -0.17
    лаÑģ
    -0.17
     nationalist
    -0.16
     Nation
    -0.16
    POSITIVE LOGITS
    -style
    0.20
     incom
    0.19
    ç¥ļ
    0.19
    绸
    0.17
    紧迫
    0.17
    اش
    0.17
    ro
    0.17
    re
    0.17
    plit
    0.17
    cie
    0.17
    Activations Density 0.008%

    No Known Activations