© 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. 11368
    Prev
    Next
    INDEX
    Explanations

    email addresses and contact info

    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
    ä¹ĭæĦı
    -0.19
    寸
    -0.19
    翦
    -0.18
    OrDefault
    -0.18
    classNames
    -0.17
    åħ¨æĸĩ
    -0.17
    Fre
    -0.17
    çļĦ空éĹ´
    -0.17
    PathParam
    -0.17
    æ§Ľ
    -0.17
    POSITIVE LOGITS
    aret
    0.21
    Xd
    0.19
     xen
    0.19
    uil
    0.18
    лик
    0.18
     viewBox
    0.17
    arro
    0.17
    æĪIJé¾Ļ
    0.17
    èī²å½©
    0.17
    æ·ŀ
    0.17
    Activations Density 0.019%

    No Known Activations