© 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. 11691
    Prev
    Next
    INDEX
    Explanations

    .util, .view, .os, ".net", ".io"

    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
    åĨľè´¸å¸Ĥåľº
    -0.23
    ä¸Ģå¹ķ
    -0.21
    åĿļå®ŀçļĦ
    -0.20
    åģľè½¦ä½į
    -0.19
    mouseup
    -0.19
    åıī
    -0.19
    azo
    -0.18
    åĩºè¡Į
    -0.18
    umni
    -0.17
    argas
    -0.17
    POSITIVE LOGITS
    æIJŃ
    0.19
     con
    0.19
    好å¤Ħ
    0.18
    _simps
    0.17
    allah
    0.17
    ç»ĨåĮĸ
    0.17
    qrst
    0.17
    enance
    0.17
    _ASC
    0.17
     Lafayette
    0.17
    Activations Density 0.283%

    No Known Activations