© 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. 12880
    Prev
    Next
    INDEX
    Explanations

    traffic congestion and 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
    çĤķ
    -0.20
    _rom
    -0.20
    éĻ¢
    -0.19
     tạp
    -0.19
    æ³ķå¾ĭ顾éĹ®
    -0.19
    èĭ¦èĭ¦
    -0.19
    eced
    -0.18
    èī²ç´ł
    -0.18
    èij³
    -0.18
     Yorkshire
    -0.18
    POSITIVE LOGITS
    æĭ¥åłµ
    0.45
     congestion
    0.38
    åłµ
    0.35
     traffic
    0.35
    æµģéĩı
    0.32
    交éĢļ
    0.29
    traffic
    0.28
    çĸı导
    0.28
    åłµå¡ŀ
    0.28
    çĵ¶é¢Ī
    0.27
    Activations Density 0.024%

    No Known Activations