© 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. 15336
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by a new sentence

    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
    obl
    -0.19
    衽
    -0.18
    ÙĪا
    -0.18
    å°¤åħ¶æĺ¯
    -0.18
    æľīæľŁ
    -0.17
    르
    -0.17
    ouis
    -0.17
    å°¤åħ¶
    -0.17
    Ỽ
    -0.17
    çī¹åĪ«æĺ¯
    -0.17
    POSITIVE LOGITS
    åįķ纯çļĦ
    0.22
    åIJĵå¾Ĺ
    0.21
    FilterWhere
    0.20
    æŀľæ±ģ
    0.18
    æ¤ħ
    0.18
    Nearly
    0.18
    çļĦæĹ¥
    0.18
    åĨľåī¯äº§åĵģ
    0.18
    æ¿ĢçĥĪçļĦ
    0.18
    身
    0.18
    Activations Density 0.038%

    No Known Activations