© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35966
    Prev
    Next
    INDEX
    Explanations

    parallel directives (omp, acc, mpi)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    èįĴ
    -0.11
    oted
    -0.10
     Studio
    -0.09
    ç¥Ģ
    -0.09
    Studio
    -0.09
    kas
    -0.09
    è·µ
    -0.09
    æ£ķ
    -0.08
    uye
    -0.08
    èĥ«
    -0.08
    POSITIVE LOGITS
    (MPI
    0.11
    	MPI
    0.11
    ellan
    0.10
    ä¸įèĤ¯
    0.10
     mpi
    0.10
    éļľç¢į
    0.09
    mpi
    0.09
     MPI
    0.09
    _mpi
    0.08
    姹
    0.08
    Activations Density 0.452%

    No Known Activations