© 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. 14999
    Prev
    Next
    INDEX
    Explanations

    "Proceedings of" or "International Conference"

    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
    yre
    -0.19
    ãģĵãĤĮãģĭãĤī
    -0.19
    æªł
    -0.19
     à¹Ģมษ
    -0.18
    ạn
    -0.18
    å®Ľ
    -0.18
    ä¸Ģå°ģ
    -0.18
    arf
    -0.18
    енÑĮк
    -0.18
     à¸ŀฤษ
    -0.18
    POSITIVE LOGITS
    ague
    0.22
     Ngo
    0.20
    rael
    0.20
    در
    0.19
    åĬĽåº¦
    0.18
    æĮ«æĬĺ
    0.18
    éĤ¨
    0.18
    ä¼ļéķ¿
    0.17
    人æŃ»äº¡
    0.17
    INGS
    0.17
    Activations Density 0.076%

    No Known Activations