© 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. 14360
    Prev
    Next
    INDEX
    Explanations

    synchronization primitives (locks, mutexes, atomic operations)

    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
    å¹³åĿĩæ°´å¹³
    -0.22
    åŃ£èĬĤ
    -0.21
    æIJŃè½½
    -0.21
    æ©IJ
    -0.20
    æīİæł¹
    -0.20
     Casc
    -0.19
    strup
    -0.19
    è¡¥é½IJ
    -0.19
    æīİ
    -0.19
    iano
    -0.19
    POSITIVE LOGITS
    éĶģ
    0.38
    .lock
    0.32
     locks
    0.32
     lock
    0.31
    lock
    0.31
    (lock
    0.30
     locking
    0.28
     Lock
    0.28
     LOCK
    0.28
    -lock
    0.27
    Activations Density 0.253%

    No Known Activations