© 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. 12397
    Prev
    Next
    INDEX
    Explanations

    numpy and scipy

    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
    æµĵ缩
    -0.24
    饰
    -0.23
    TAIL
    -0.21
    pcf
    -0.21
    墨
    -0.20
    æĪĴ
    -0.19
    尾巴
    -0.19
    ckt
    -0.19
    èĥ¸éĥ¨
    -0.19
    tails
    -0.19
    POSITIVE LOGITS
     numpy
    0.27
     Matlab
    0.26
     MATLAB
    0.25
    (numpy
    0.24
    numpy
    0.23
    _numpy
    0.23
    .ndarray
    0.23
     matlab
    0.22
     scipy
    0.22
    MPI
    0.22
    Activations Density 0.482%

    No Known Activations