© 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. 10980
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĬ©éķ¿
    -0.20
    幺
    -0.20
    ä¸Ńè¶ħ
    -0.19
    åļ£
    -0.18
     lá»Ńa
    -0.18
    央
    -0.18
     footh
    -0.18
    鹤
    -0.17
    uma
    -0.17
    emat
    -0.17
    POSITIVE LOGITS
    æģ¯
    0.19
    è¿Ĥ
    0.19
    ihu
    0.19
    èĩ¾
    0.18
    edom
    0.18
    ä¼łæŁĵçĹħ
    0.18
    天ä¸ĭ
    0.17
    循
    0.17
    idget
    0.17
    天é¹ħ
    0.17
    Activations Density 0.000%

    No Known Activations