© 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. 11472
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    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
    ãģ¤ãģĭ
    -0.20
    å§ĺ
    -0.19
    æĴij
    -0.19
    kich
    -0.19
    pread
    -0.18
    propri
    -0.18
    ,GL
    -0.18
    ioc
    -0.18
     ØŃاج
    -0.17
    -License
    -0.17
    POSITIVE LOGITS
    åIJijåīį
    0.21
    èIJ
    0.21
    ä¸įçķĻ
    0.20
    ä¹ĭæĺŁ
    0.20
    é¢ijéģĵ
    0.20
    赶
    0.20
    çľĭçĤ¹
    0.19
    hunt
    0.19
     cascade
    0.19
    <D
    0.19
    Activations Density 0.265%

    No Known Activations