© 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. 11817
    Prev
    Next
    INDEX
    Explanations

    over a quantity

    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
     si
    -0.18
    éħŀ
    -0.18
    -and
    -0.17
     honor
    -0.17
     se
    -0.17
    ä¸Ģ次次
    -0.17
    /or
    -0.17
    ä¾Ŀæį®
    -0.17
    :*
    -0.16
     err
    -0.16
    POSITIVE LOGITS
    ä¸įåħĭ
    0.22
    tings
    0.20
     nữa
    0.19
     ÐIJлекÑģан
    0.18
    ç¦ıå¾·
    0.17
    è´¢
    0.17
     trần
    0.17
    æĪ¾
    0.17
     ÐĶмиÑĤÑĢ
    0.16
    uds
    0.16
    Activations Density 0.033%

    No Known Activations