© 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. 15203
    Prev
    Next
    INDEX
    Explanations

    MHz networks, styled shoots, Sega

    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
    бо
    -0.19
    æĪ¢
    -0.17
    ç¨Ĺ
    -0.17
    饽
    -0.16
    ä¾Ķ
    -0.16
     åķ
    -0.15
    ç²¹
    -0.15
    arin
    -0.15
    åįĬ天
    -0.15
     Braz
    -0.15
    POSITIVE LOGITS
     fanc
    0.16
    elta
    0.15
    redients
    0.15
    /disable
    0.15
    ysis
    0.15
    psilon
    0.14
    tics
    0.14
    MMdd
    0.14
    ettle
    0.14
    )x
    0.13
    Activations Density 2.263%

    No Known Activations