© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12296
    Prev
    Next
    INDEX
    Explanations

    arrival / arriving

    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
    .salary
    -0.20
    éľ²å¤©
    -0.19
     internal
    -0.19
     Apprentice
    -0.19
    ihad
    -0.18
     bü
    -0.18
    符åı·
    -0.18
     horn
    -0.18
     interior
    -0.18
    æĤ¬
    -0.18
    POSITIVE LOGITS
    åħ¥ä½ı
    0.28
    æĭİ
    0.24
     arrivals
    0.24
     arrival
    0.23
     Arrival
    0.23
    çļĦåĪ°æĿ¥
    0.23
     arrive
    0.20
    é¦ĸæī¹
    0.20
    /start
    0.20
    Ending
    0.20
    Activations Density 0.020%

    No Known Activations