© 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. 12017
    Prev
    Next
    INDEX
    Explanations

    discussion

    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
    CONF
    -0.20
     conf
    -0.19
    å¤ĩæ¡Ī
    -0.18
     gag
    -0.18
    åĩºç¤º
    -0.18
    eding
    -0.17
     Brom
    -0.17
    Ã¼ÃŁ
    -0.17
     sp
    -0.17
     Woods
    -0.17
    POSITIVE LOGITS
    è¯Ŀé¢ĺ
    0.27
    è¨İè«ĸ
    0.20
    åı½
    0.20
    kol
    0.20
    ä¼ĹæīĢåij¨çŁ¥
    0.20
    讨论
    0.19
    ä¸ĵåĮº
    0.19
    åıįæĩī
    0.19
    æĤłæĤł
    0.19
    åıįåºĶ
    0.19
    Activations Density 0.018%

    No Known Activations