© 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. 16105
    Prev
    Next
    INDEX
    Explanations

    fictional names and settings

    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
     Melania
    -0.22
    åĩºæ±Ĺ
    -0.21
    åIJĮåŁİ
    -0.20
    ition
    -0.20
    æ¶Ī
    -0.19
    insic
    -0.18
     Äijoán
    -0.18
    å·¥ä½ľèĢħ
    -0.18
    奢ä¾Īåĵģ
    -0.18
    оÑī
    -0.17
    POSITIVE LOGITS
     fictional
    0.46
    èĻļæŀĦ
    0.39
    fiction
    0.34
     fict
    0.31
     hypothetical
    0.29
     fiction
    0.28
     Fiction
    0.27
    åľºæĻ¯
    0.27
    æķħäºĭ
    0.25
    å°ı说
    0.24
    Activations Density 0.317%

    No Known Activations