© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2562
    Prev
    Next
    INDEX
    Explanations

    parallel processing and threads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    Ending
    -0.27
     Ending
    -0.24
     stalking
    -0.23
    建档
    -0.22
    å±¥
    -0.22
     inaccurate
    -0.22
    dé
    -0.22
    çĹķ
    -0.22
     maté
    -0.22
    æľīåħ³è§Ħå®ļ
    -0.22
    POSITIVE LOGITS
     worker
    0.37
     parallel
    0.37
     threads
    0.37
     workers
    0.35
    -workers
    0.35
    åħħåĪĨåĪ©çĶ¨
    0.34
    parallel
    0.34
     ThreadPool
    0.34
    Workers
    0.34
    _THREADS
    0.34
    Activations Density 0.152%

    No Known Activations