© 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. 12548
    Prev
    Next
    INDEX
    Explanations

    Kashmir, Yosemite, Sahara, Kapoor, Robert

    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
    ä¸Ŀä¸Ŀ
    -0.20
    讦
    -0.19
    eks
    -0.18
    лег
    -0.18
    æ¯įæł¡
    -0.17
    å¤ļæł·
    -0.16
    å¿Ŀ
    -0.16
    ฯ
    -0.16
    Traits
    -0.15
     inexpensive
    -0.15
    POSITIVE LOGITS
    ly
    0.21
    人åĿĩ
    0.20
    idar
    0.20
    ria
    0.18
    trak
    0.18
    êu
    0.17
    ward
    0.17
    wards
    0.17
    bid
    0.17
    ï¸
    0.17
    Activations Density 0.002%

    No Known Activations