© 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. 15984
    Prev
    Next
    INDEX
    Explanations

    traffic flow

    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
    agraph
    -0.20
    lug
    -0.19
    èĢĥåľº
    -0.19
    åĢ®
    -0.18
    OMPI
    -0.18
    éĻŁ
    -0.17
    ogi
    -0.17
    zes
    -0.17
    绶
    -0.17
    妥åĸĦ
    -0.17
    POSITIVE LOGITS
    æµģéĩı
    0.29
    人æ°Ķ
    0.24
    éĩı
    0.23
     flows
    0.22
    æºIJ
    0.22
    chan
    0.21
     flow
    0.21
    æĿ¥æºIJ
    0.20
    注æĦıåĬĽ
    0.20
    æĢ»éĩı
    0.19
    Activations Density 0.013%

    No Known Activations