© 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. 11370
    Prev
    Next
    INDEX
    Explanations

    version control commit messages

    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
     exc
    -0.21
     suit
    -0.20
    å½¢æĪIJ
    -0.19
     chances
    -0.19
     counter
    -0.19
    ery
    -0.19
     strongly
    -0.19
    带走
    -0.19
    worm
    -0.19
    ©
    -0.19
    POSITIVE LOGITS
     wida
    0.26
     echang
    0.25
    æĸĩåĮĸä¼łæĴŃ
    0.22
    'gc
    0.22
     odense
    0.22
    _ComCallableWrapper
    0.22
    >manual
    0.21
     spep
    0.21
    ä¹ĭ乡
    0.21
    ERSHEY
    0.21
    Activations Density 0.010%

    No Known Activations