© 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. 10915
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
    å¾Īå¿«
    -0.20
    åı£è¢ĭ
    -0.20
    puted
    -0.20
    ickers
    -0.19
    ä»Ĭ年以æĿ¥
    -0.19
    第ä¸īèĬĤ
    -0.18
    æĽ´å¤§çļĦ
    -0.18
    åĵªéĩĮ
    -0.18
    æľ¬åij¨
    -0.18
    å·¦åı³
    -0.18
    POSITIVE LOGITS
     years
    0.22
    å²ģæľĪ
    0.22
     ago
    0.22
    WARD
    0.21
    å¤ļå¹´
    0.20
    ward
    0.20
    æªĢ
    0.20
    -old
    0.19
    years
    0.19
    åĽŀé¦ĸ
    0.19
    Activations Density 0.037%

    No Known Activations